© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 135295
    Prev
    Next
    INDEX
    Explanations

    drug offenses, vote counts, birth certificate

    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_262k_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
    ┓
    0.46
    ◘
    0.46
    𝙪
    0.44
    वाणी
    0.44
    肓
    0.43
    чня
    0.43
    UnaryOperation
    0.41
    𝙶
    0.40
    𝒕
    0.40
    苻
    0.40
    POSITIVE LOGITS
     SELL
    0.40
    poses
    0.40
     MAIN
    0.40
     bir
    0.39
     eje
    0.39
     birt
    0.38
     births
    0.38
    lden
    0.38
     Bir
    0.37
     Selling
    0.37
    Activations Density 0.007%

    No Known Activations