© 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. 125973
    Prev
    Next
    INDEX
    Explanations

    Fuse Box

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

    presets, downloads, giving, subordinates

    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
    ৭
    0.47
     elevado
    0.46
    chemia
    0.45
    ≫
    0.45
    Solar
    0.45
    N
    0.44
    😗
    0.44
    0.43
     fanciful
    0.43
    bell
    0.42
    POSITIVE LOGITS
     PIL
    0.47
     Depart
    0.46
    耖
    0.45
     баста
    0.44
     Seychelles
    0.43
     whakar
    0.43
     STARTED
    0.43
     whakap
    0.43
    ච්
    0.43
     pilotes
    0.43
    Activations Density 0.001%

    No Known Activations