© 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. 180948
    Prev
    Next
    INDEX
    Explanations

    away from

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

    away from

    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
    ar
    0.76
     दट
    0.69
    が含ま
    0.66
    {//
    0.64
    ak
    0.64
    on
    0.61
    मा
    0.60
     it
    0.59
     U
    0.58
    '
    0.58
    POSITIVE LOGITS
    но
    1.01
     AWAY
    0.92
    я
    0.86
    o
    0.84
     Away
    0.83
    Away
    0.83
    ,
    0.81
     away
    0.80
    k
    0.78
    số
    0.78
    Activations Density 0.265%

    No Known Activations