© 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. 73179
    Prev
    Next
    INDEX
    Explanations

    sections and divisions

    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
    from
    -1.18
     даже
    -1.13
     их
    -1.07
     even
    -1.02
     from
    -0.99
     diminta
    -0.98
    楯
    -0.97
     созда
    -0.97
     wirklich
    -0.94
     mengirim
    -0.93
    POSITIVE LOGITS
    ,
    1.14
     we
    1.05
     will
    1.02
     enthou
    0.99
    دهی
    0.96
     bloed
    0.94
    讨厌
    0.94
    şağı
    0.93
    pain
    0.92
     euc
    0.92
    Activations Density 0.007%

    No Known Activations