© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 58065
    Prev
    Next
    INDEX
    Explanations

    technology, European, verdict, Russian

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

    zip files

    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
     각
    0.50
     takt
    0.49
     Λ
    0.46
     passos
    0.45
     Maß
    0.45
     윤
    0.45
     Ante
    0.44
    𒊑
    0.44
     被
    0.43
     Vai
    0.43
    POSITIVE LOGITS
    ávají
    0.48
    news
    0.45
    ani
    0.43
    he
    0.42
    ácie
    0.41
    obile
    0.41
    his
    0.41
    oh
    0.40
    ңү
    0.40
    ienen
    0.40
    Activations Density 0.000%

    No Known Activations