© 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. 65283
    Prev
    Next
    INDEX
    Explanations

    technical or specific acronyms

    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
    iPod
    -0.96
    ються
    -0.94
    त्या
    -0.93
     tỷ
    -0.93
     ち
    -0.92
     voltak
    -0.90
    ャ
    -0.90
    ∷
    -0.90
     zelfs
    -0.89
    refour
    -0.89
    POSITIVE LOGITS
    smaller
    0.93
    同じ
    0.89
    limpiar
    0.88
    ・・・・・
    0.87
    with
    0.87
     in
    0.87
    without
    0.86
    。"
    0.84
     potret
    0.80
     одежду
    0.80
    Activations Density 0.269%

    No Known Activations