© 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. 48201
    Prev
    Next
    INDEX
    Explanations

    edit distance matrix

    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
     Cables
    0.44
     age
    0.43
    谒
    0.41
     Age
    0.38
     cables
    0.38
    age
    0.37
    reich
    0.37
     AGE
    0.36
     chub
    0.36
     chai
    0.36
    POSITIVE LOGITS
    行
    0.37
    Multipart
    0.36
     TokenType
    0.36
    inputType
    0.36
     tepat
    0.35
     स्ट्र
    0.35
    ulkan
    0.35
     Partai
    0.35
    ൬
    0.35
     ვ
    0.35
    Activations Density 0.034%

    No Known Activations