© 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. 225277
    Prev
    Next
    INDEX
    Explanations

    adjunct instructor

    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
    ownic
    0.48
    BMC
    0.46
    arya
    0.45
    amad
    0.45
    AMC
    0.45
    getConfig
    0.44
    倆
    0.43
    ueba
    0.43
    adee
    0.42
    Validate
    0.42
    POSITIVE LOGITS
     cellules
    0.52
     강
    0.49
    ୃ
    0.49
     appliqu
    0.47
     récentes
    0.47
     envelopp
    0.47
     absol
    0.47
    сну
    0.47
     ostatnich
    0.47
    وا
    0.46
    Activations Density 0.000%

    No Known Activations