© 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. 216382
    Prev
    Next
    INDEX
    Explanations

    specific activities or concepts

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

    academic progress and future events

    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
    ienst
    0.49
    न्स
    0.48
    ﺏ
    0.46
    SIGNED
    0.46
    itaan
    0.46
    soap
    0.45
    VENDOR
    0.45
     কলে
    0.45
     নম
    0.44
    िन्
    0.44
    POSITIVE LOGITS
     avancé
    0.49
     적
    0.47
     majeure
    0.47
    ographiques
    0.46
     outlaw
    0.46
     privy
    0.44
     예
    0.44
    독
    0.43
     awaken
    0.42
    тар
    0.42
    Activations Density 0.000%

    No Known Activations