© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202671
    Prev
    Next
    INDEX
    Explanations

    junk cars, cancer, clusters

    np_acts-logits-general · gemini-2.5-flash-lite

    transformation and evolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demanda
    0.46
     Eyre
    0.46
     Stalingrad
    0.44
     Tajikistan
    0.41
     baku
    0.41
     cenderung
    0.40
     diagonal
    0.40
     [(
    0.40
     genial
    0.40
     [*
    0.40
    POSITIVE LOGITS
    гов
    0.50
     Built
    0.46
    maier
    0.46
    ၠ
    0.46
    Built
    0.46
    ქვ
    0.45
     Operational
    0.45
    uciones
    0.45
    힘
    0.43
    Operational
    0.43
    Activations Density 0.000%

    No Known Activations