© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101239
    Prev
    Next
    INDEX
    Explanations

    code constructs or file paths

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

    line continuation characters or symbols in code, particularly underscores and ampersands used for splitting long statements across multiple lines.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    '
    -2.22
    }
    -2.05
    *
    -1.77
    -1.76
    {
    -1.73
    providedIn
    -1.72
    …”
    -1.60
    -1.58
    (
    -1.58
     ‘
    -1.58
    POSITIVE LOGITS
     Этот
    2.20
     Roughly
    2.17
     Таким
    1.97
     Practically
    1.91
     Anyone
    1.87
    ETHING
    1.86
     Thousands
    1.86
     Hoping
    1.85
     Allowing
    1.84
     Earlier
    1.83
    Activations Density 0.001%

    No Known Activations