© 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-65K
    7. 55396
    Prev
    Next
    INDEX
    Explanations

    specific titles and descriptions

    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_65k_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
    ima
    0.31
    api
    0.31
    is
    0.30
    iam
    0.30
    ়
    0.29
    xt
    0.29
    i
    0.29
    ium
    0.29
    ih
    0.29
    bole
    0.29
    POSITIVE LOGITS
    OTROS
    0.29
     також
    0.29
     вважа
    0.29
    ベスト
    0.29
     DIRECTOR
    0.28
     perplexing
    0.28
    wärt
    0.27
    愜
    0.26
     پاب
    0.26
    VERE
    0.26
    Activations Density 0.028%

    No Known Activations