© 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. 19374
    Prev
    Next
    INDEX
    Explanations

    features and descriptions

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

    listing pros and cons

    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
    сора
    0.45
    치를
    0.40
    áférés
    0.39
    undaki
    0.39
    🏅
    0.38
    acterísticas
    0.38
    जिसे
    0.38
    Emoji
    0.37
    ēi
    0.37
     которого
    0.37
    POSITIVE LOGITS
    ：
    0.42
    ؛
    0.41
     bosonic
    0.40
    dq
    0.38
    ः
    0.38
     ؛
    0.36
    dL
    0.36
    ઃ
    0.36
    ;;)
    0.36
    ；
    0.36
    Activations Density 0.001%

    No Known Activations