© 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. 70927
    Prev
    Next
    INDEX
    Explanations

    who might post

    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
    Alors
    0.50
     অধিবেশ
    0.49
    統領
    0.48
     कॉरिडोर
    0.48
    ালিয়া
    0.46
    ▽
    0.46
    অন
    0.46
     Todo
    0.45
    મુ
    0.44
    drawiam
    0.44
    POSITIVE LOGITS
     subjective
    0.46
     nyeri
    0.44
     klien
    0.43
     Higgins
    0.42
     eig
    0.42
     progeny
    0.41
     использова
    0.40
     വേദന
    0.40
     cockroaches
    0.40
    ʊ
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.