© 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. 192314
    Prev
    Next
    INDEX
    Explanations

    protect your

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

    academic research, outdoor clothing, Python code

    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
    氀
    0.45
    acqu
    0.43
    Nel
    0.43
     prepara
    0.42
    only
    0.41
     ограничения
    0.41
     pivoting
    0.41
    *,
    0.40
     besø
    0.40
     अँ
    0.40
    POSITIVE LOGITS
     defamatory
    0.46
     Ejército
    0.45
     disgruntled
    0.45
     Betfair
    0.44
     Apostolic
    0.44
    фициа
    0.43
     Humanitarian
    0.43
     whistleblower
    0.42
    isValue
    0.42
     برضو
    0.41
    Activations Density 0.001%

    No Known Activations