© 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. 210454
    Prev
    Next
    INDEX
    Explanations

    you to be

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

    qualities and dimensions

    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
    B
    0.56
    AST
    0.43
     platos
    0.43
    D
    0.42
    𝙱
    0.42
    奐
    0.42
    Jlc
    0.42
    ضل
    0.41
     baffling
    0.41
    P
    0.41
    POSITIVE LOGITS
     olej
    0.48
     CentOS
    0.47
     médecin
    0.46
     அறிந்து
    0.46
     ਵਰ
    0.46
     Accueil
    0.45
     よ
    0.45
     ફી
    0.45
     confidentialité
    0.45
    volle
    0.45
    Activations Density 0.000%

    No Known Activations