© 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-16K
    7. 6752
    Prev
    Next
    INDEX
    Explanations

    parts of

    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_16k_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
    6
    0.73
    OP
    0.73
    0
    0.71
    5
    0.69
    9
    0.64
     merkez
    0.63
    W
    0.63
    4
    0.61
    AP
    0.59
    ET
    0.59
    POSITIVE LOGITS
    parts
    1.08
     parts
    1.06
     Parts
    0.93
    Parts
    0.93
    部件
    0.84
     partes
    0.83
    teile
    0.82
     Teile
    0.82
     частини
    0.82
     частей
    0.81
    Activations Density 0.176%

    No Known Activations