© 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. 141678
    Prev
    Next
    INDEX
    Explanations

    activate a puzzle

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

    unify much

    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
    az
    0.62
    s
    0.62
    at
    0.61
    il
    0.59
    ar
    0.59
    it
    0.58
    g
    0.55
    es
    0.54
    im
    0.52
    ac
    0.52
    POSITIVE LOGITS
     vrste
    0.48
     hyperparameters
    0.47
     skill
    0.46
     possibilidades
    0.46
     placa
    0.45
    সম্পাদকীয়
    0.45
     tarm
    0.45
     cube
    0.44
     hunger
    0.44
     indivíduos
    0.44
    Activations Density 0.000%

    No Known Activations