© 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. 10-GEMMASCOPE-RES-131K
    7. 21151
    Prev
    Next
    INDEX
    Explanations

    field, hello, united, mycobacterium, agonistic

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

    parts of words that form the beginning syllables of terms, particularly in formatted documents or technical content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     focusing
    -1.91
     embracing
    -1.75
     this
    -1.73
     those
    -1.70
     To
    -1.70
     That
    -1.69
     while
    -1.62
     regarding
    -1.59
     surprisingly
    -1.59
    Surprisingly
    -1.57
    POSITIVE LOGITS
    毟
    1.85
    ⎔
    1.72
    бол
    1.71
     ámbitos
    1.71
    锨
    1.68
     boister
    1.65
    〮
    1.65
    американ
    1.65
    
    1.65
    蠓
    1.63
    Activations Density 0.073%

    No Known Activations