© 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. 103038
    Prev
    Next
    INDEX
    Explanations

    liability, behaviour, downsizing

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

    LDAP structure or network components

    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
    r
    0.56
    də
    0.55
    ার্চ
    0.53
    ACH
    0.52
    dür
    0.52
    nich
    0.52
     причиной
    0.52
    i
    0.50
    có
    0.50
    THERE
    0.49
    POSITIVE LOGITS
     College
    0.55
    uzzles
    0.45
     semi
    0.45
     Planning
    0.44
    驩
    0.44
    にも
    0.44
     Structural
    0.43
    結構
    0.43
    ไง
    0.43
     lan
    0.42
    Activations Density 0.000%

    No Known Activations