© 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. 148990
    Prev
    Next
    INDEX
    Explanations

    simple site menu

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

    Mathematica and discord code

    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
     SIRT
    0.44
     ER
    0.43
     CRISPR
    0.41
     Color
    0.41
     Quantification
    0.41
     Oxy
    0.40
     offline
    0.40
    /
    0.40
     genü
    0.39
     SKU
    0.39
    POSITIVE LOGITS
    yecto
    0.57
    descricao
    0.55
    މ
    0.55
     empezar
    0.53
    ASDW
    0.52
    ciaux
    0.52
     ફરિયા
    0.51
    𒌓
    0.51
     comienzo
    0.51
    חיל
    0.50
    Activations Density 0.003%

    No Known Activations