© 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. 48369
    Prev
    Next
    INDEX
    Explanations

    html language attribute english

    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
     Preservation
    0.44
     च
    0.42
     elephants
    0.41
     र
    0.39
     nChar
    0.39
     elephant
    0.39
    🐘
    0.39
    ið
    0.38
     Oriental
    0.37
     Dans
    0.37
    POSITIVE LOGITS
    менова
    0.42
    धपुर
    0.38
    Tela
    0.38
    epen
    0.38
    prayer
    0.38
    itatif
    0.37
    ignet
    0.37
    oney
    0.37
     berger
    0.37
    igenous
    0.37
    Activations Density 0.000%

    No Known Activations