© 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. 193012
    Prev
    Next
    INDEX
    Explanations

    store or premises

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

    forget loans for now

    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
    VU
    0.52
    terase
    0.50
    PSR
    0.49
     placebo
    0.47
     VU
    0.47
    SCPC
    0.46
    ᡧ
    0.45
    Lit
    0.44
    பல
    0.44
     INIS
    0.44
    POSITIVE LOGITS
     Naam
    0.48
     Abbott
    0.45
    :
    0.45
     أ
    0.45
     yönt
    0.44
    ’
    0.44
     Ahmed
    0.44
     ။
    0.43
     پہلی
    0.43
     හේ
    0.43
    Activations Density 0.001%

    No Known Activations