© 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. 15514
    Prev
    Next
    INDEX
    Explanations

    import statements in code

    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
    ('*
    -0.87
     INDUSTR
    -0.83
     mourir
    -0.81
     замести
    -0.80
     صورت
    -0.79
    niku
    -0.79
    ノン
    -0.79
     polegadas
    -0.79
     chim
    -0.78
     LABORATOR
    -0.78
    POSITIVE LOGITS
     myös
    1.13
     帶
    0.99
     también
    0.97
     także
    0.93
     גם
    0.93
     also
    0.91
     seguirá
    0.91
    っていますが
    0.90
     trabaj
    0.90
    UMNS
    0.90
    Activations Density 0.000%

    No Known Activations