© 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. 174148
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

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

    Google Weather

    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
     effluents
    0.52
     tracheal
    0.47
     dampers
    0.47
    부분
    0.46
     quies
    0.46
     respir
    0.45
    ۔
    0.45
     spasms
    0.44
     trachea
    0.44
     infidelity
    0.44
    POSITIVE LOGITS
    <0x80>
    0.55
    0
    0.49
     name
    0.47
     solche
    0.45
     lecturer
    0.44
    painter
    0.44
    macher
    0.44
    ০০
    0.44
     painter
    0.44
    贼
    0.43
    Activations Density 0.000%

    No Known Activations