© 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. 167978
    Prev
    Next
    INDEX
    Explanations

    safety during activity

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

    contrast or addition

    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
     लड़का
    0.50
     जिसका
    0.48
     kidn
    0.47
    દ્ધ
    0.47
    soldiers
    0.47
    troops
    0.47
     cheek
    0.46
    ँ
    0.46
     רק
    0.45
     φ
    0.44
    POSITIVE LOGITS
    Coordinator
    0.45
    בא
    0.44
    Binder
    0.44
    Bibli
    0.43
    াবলীর
    0.43
     Accessibility
    0.43
    Genero
    0.43
    AVER
    0.43
    Архи
    0.42
    ApiException
    0.42
    Activations Density 0.000%

    No Known Activations