© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3959
    Prev
    Next
    INDEX
    Explanations

    advanced bullet point features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     If
    0.95
    3
    0.94
     attachment
    0.93
    If
    0.86
    quad
    0.86
     West
    0.78
     umbilical
    0.78
     rent
    0.74
     Attachment
    0.73
     proud
    0.73
    POSITIVE LOGITS
    zis
    1.61
    mata
    1.54
     resumen
    1.49
    antina
    1.43
     législ
    1.43
    azo
    1.43
    纲
    1.42
    ilte
    1.42
     Slug
    1.41
     Barcl
    1.39
    Activations Density 0.138%

    No Known Activations