© 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. 40-GEMMASCOPE-2-RES-65K
    7. 48481
    Prev
    Next
    INDEX
    Explanations

    translate to languages

    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_40_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
     envis
    0.42
    忆
    0.38
     finances
    0.38
    心が
    0.38
     Marcel
    0.37
     liqueur
    0.37
     vz
    0.37
     অনুপস্থিত
    0.37
    ைகளால்
    0.36
    𝑃
    0.36
    POSITIVE LOGITS
    itans
    0.44
     есть
    0.42
    yu
    0.41
    bling
    0.40
    aln
    0.40
    చ్చే
    0.40
     구분
    0.40
     strtotime
    0.39
    enting
    0.38
    forestation
    0.38
    Activations Density 0.003%

    No Known Activations