© 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. 63088
    Prev
    Next
    INDEX
    Explanations

    annual / disclaimer / diabetes / business

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

    natural language sentences

    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
     palvel
    0.52
     anarch
    0.50
     services
    0.47
     Amnesty
    0.47
    am
    0.46
    ide
    0.46
     alk
    0.45
    0
    0.45
    essa
    0.44
    expert
    0.44
    POSITIVE LOGITS
    шибка
    0.57
    ありました
    0.55
    Ⴀ
    0.54
     GridLayout
    0.50
     призна
    0.48
    )!=
    0.48
     выражения
    0.48
    дри
    0.48
    UpdateChoice
    0.47
     резко
    0.47
    Activations Density 0.000%

    No Known Activations