© 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. 187546
    Prev
    Next
    INDEX
    Explanations

    Parliament that claimed

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

    star or Chinese

    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
    σι
    0.52
    л
    0.50
    ding
    0.50
     og
    0.50
    m
    0.50
    μα
    0.49
    <0xA5>
    0.48
    름
    0.47
     or
    0.46
    có
    0.45
    POSITIVE LOGITS
     сельскохозяй
    0.50
     aldehyde
    0.46
     உலகம்
    0.46
     linearly
    0.46
     phosphorylated
    0.44
     ఇందు
    0.44
    sulph
    0.44
     corticosteroids
    0.44
     вертика
    0.44
     phospholipids
    0.43
    Activations Density 0.000%

    No Known Activations