© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111535
    Prev
    Next
    INDEX
    Explanations

    imports and functions

    np_acts-logits-general · gemini-2.5-flash-lite

    statements that prevent default browser or event behavior in code, particularly `preventDefault()` calls and control flow interruptions like `break` or `pass`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is looking for stretches of code indentation whitespace (long runs of spaces/tabs at the start of lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -1.50
     Inſ
    -1.42
    лят
    -1.33
     ✔️
    -1.30
    ㄸ
    -1.27
    可以
    -1.25
     conhecido
    -1.24
     easiest
    -1.23
     การ
    -1.21
    是最
    -1.21
    POSITIVE LOGITS
     ktore
    1.72
     or
    1.70
     mój
    1.59
    that
    1.55
    ("")]
    1.53
    if
    1.53
    \}$.
    1.52
    ]$.
    1.48
    </sup>
    1.45
    ’.
    1.45
    Activations Density 0.001%

    No Known Activations