© 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. 70483
    Prev
    Next
    INDEX
    Explanations

    especially or even followed by preposition

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

    python functions for math

    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
    ol
    0.74
    OL
    0.73
    av
    0.70
    ug
    0.70
    ab
    0.70
    OC
    0.69
    K
    0.69
    OD
    0.67
    də
    0.66
    CH
    0.66
    POSITIVE LOGITS
    л
    0.96
    in
    0.89
     and
    0.87
    ン
    0.84
    ка
    0.82
    كد
    0.80
    с
    0.79
     و
    0.76
    х
    0.73
    ك
    0.73
    Activations Density 0.000%

    No Known Activations