© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205921
    Prev
    Next
    INDEX
    Explanations

    radiology toolbox pro

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

    password, run, content, or water

    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
    Negative Logits
     bloquear
    0.58
     exclus
    0.54
     keamanan
    0.52
    㶲
    0.50
     dailySales
    0.49
    plein
    0.48
    fdata
    0.47
     במהלך
    0.47
     mwen
    0.47
     стоимость
    0.47
    POSITIVE LOGITS
     Withdrawal
    0.50
    λώ
    0.48
    க்கண
    0.48
     Kentucky
    0.47
    ема
    0.46
    らなかった
    0.46
    <0x0C>
    0.45
    COVERY
    0.45
    ो
    0.44
     Tennessee
    0.43
    Activations Density 0.001%

    No Known Activations