© 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. 64967
    Prev
    Next
    INDEX
    Explanations

    import statements

    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_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
     what
    -1.13
     same
    -1.13
    зия
    -1.08
     recent
    -1.06
     went
    -1.02
     to
    -1.01
     try
    -0.99
    All
    -0.96
     attempt
    -0.93
    ържа
    -0.93
    POSITIVE LOGITS
    Lutz
    1.20
     decorativos
    1.19
    edero
    1.16
     PRACTICE
    1.13
    though
    1.12
    enity
    1.12
    Luxem
    1.09
    了过来
    1.08
    ophanes
    1.07
    resource
    1.06
    Activations Density 0.005%

    No Known Activations