© 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. 54998
    Prev
    Next
    INDEX
    Explanations

    included, excluded, officers, decisions

    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
    ங்கும்
    0.47
    景观
    0.46
    çant
    0.45
    尴
    0.45
    气候
    0.44
    痉
    0.44
     패턴
    0.43
     bloque
    0.43
    珽
    0.43
    髂
    0.43
    POSITIVE LOGITS
    ’
    0.45
     toiletries
    0.43
     Muni
    0.42
    小米
    0.41
     sache
    0.40
     welke
    0.40
    naire
    0.40
     Xiaomi
    0.40
     Jh
    0.40
     compras
    0.39
    Activations Density 0.014%

    No Known Activations