© 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. 124014
    Prev
    Next
    INDEX
    Explanations

    office, domain, deep powder

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

    litter box, ransomware strain, answer questions

    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
    იმ
    0.47
     ধারণ
    0.45
    \\
    0.44
    Arnold
    0.44
    KR
    0.43
    ikation
    0.43
    licting
    0.43
    \
    0.43
    スケジュール
    0.42
    าศ
    0.42
    POSITIVE LOGITS
     органами
    0.49
     tigris
    0.48
     organi
    0.47
     pubb
    0.47
     ultimo
    0.46
    孺
    0.46
     troubles
    0.45
     animados
    0.45
    ឈ្មោះ
    0.45
     progr
    0.44
    Activations Density 0.000%

    No Known Activations