© 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. 212883
    Prev
    Next
    INDEX
    Explanations

    numbers and specific topics

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

    most commonanonymous admirerhabit

    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
    驄
    0.47
    粦
    0.46
     продукты
    0.46
    入れて
    0.46
    ності
    0.45
    ጷ
    0.45
    約
    0.45
    牠
    0.44
    悰
    0.44
    歟
    0.44
    POSITIVE LOGITS
     Bart
    0.54
    a
    0.53
     scooter
    0.48
    Bart
    0.48
    the
    0.46
     Maruti
    0.45
     Carver
    0.43
     BMX
    0.43
    ton
    0.43
    tt
    0.42
    Activations Density 0.000%

    No Known Activations