© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2844
    Prev
    Next
    INDEX
    Explanations

    content appropriateness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     sécurité
    1.85
     কাছাকাছি
    1.82
    čit
    1.77
     ribbed
    1.77
    फ
    1.72
     objection
    1.70
    ्हे
    1.69
    fak
    1.68
    ܡ
    1.66
    ystring
    1.65
    POSITIVE LOGITS
    s
    1.62
     urn
    1.57
    scape
    1.54
     we
    1.54
    SCAPE
    1.47
     swoop
    1.45
    Scape
    1.42
     capture
    1.42
     ολο
    1.40
     заре
    1.40
    Activations Density 0.000%

    No Known Activations