© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184189
    Prev
    Next
    INDEX
    Explanations

    bellyHOW Dark window tint

    np_acts-logits-general · gemini-2.5-flash-lite

    colors and mixing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Neha
    0.49
     توسط
    0.46
    Started
    0.45
    Treat
    0.45
     ಬದಲ
    0.45
    酽
    0.45
    Rat
    0.45
    ranton
    0.44
    ")))
    0.44
    鈽
    0.43
    POSITIVE LOGITS
    residual
    0.50
    urus
    0.49
     residual
    0.49
    <0x89>
    0.46
    ઓના
    0.46
     beneficial
    0.46
     purchasers
    0.45
    成员
    0.45
    то
    0.44
     membres
    0.44
    Activations Density 0.000%

    No Known Activations