© 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. 34-GEMMASCOPE-RES-131K
    7. 92625
    Prev
    Next
    INDEX
    Explanations

    titles or specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     which
    -1.31
     many
    -1.17
     what
    -0.96
     kirj
    -0.96
    عود
    -0.93
     because
    -0.91
     wholly
    -0.89
     quite
    -0.89
     using
    -0.88
     several
    -0.85
    POSITIVE LOGITS
    COL
    0.98
     unbelievably
    0.98
     Performs
    0.90
     compleanno
    0.90
     exceptionally
    0.88
     dilapidated
    0.88
     เมื่อ
    0.86
    telser
    0.84
    (-)
    0.82
    igration
    0.82
    Activations Density 0.000%

    No Known Activations