© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16119
    Prev
    Next
    INDEX
    Explanations

    words followed by specific continuations

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

    The neuron detects block‐structure delimiters—e.g. closing braces “}” in code and “>” quote markers in emails.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    another
    -1.41
     DialogResult
    -1.22
     حوالي
    -1.17
    𝗖
    -1.17
     TextInputType
    -1.16
    significantly
    -1.15
     JsonResponse
    -1.13
     Estoy
    -1.13
    ·
    -1.13
    including
    -1.12
    POSITIVE LOGITS
     will
    1.34
     what
    1.20
     could
    1.09
     and
    1.08
     has
    1.02
    ↵↵
    1.01
     deği
    0.99
    <eos>
    0.98
    ↵↵↵↵
    0.96
    Neder
    0.96
    Activations Density 0.000%

    No Known Activations