© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91387
    Prev
    Next
    INDEX
    Explanations

    building specific things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Č
    0.46
     Boc
    0.43
    ওয়ে
    0.40
     sábado
    0.39
     ELSE
    0.39
     &-
    0.39
    嚥
    0.39
     ن
    0.39
    ဆောင်
    0.38
     Podemos
    0.38
    POSITIVE LOGITS
    Data
    0.46
    ་
    0.44
    กฏ
    0.44
    Disable
    0.43
    tais
    0.43
    qtd
    0.42
    据说
    0.41
    عب
    0.41
    Before
    0.41
    aird
    0.41
    Activations Density 0.011%

    No Known Activations