© 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. 18696
    Prev
    Next
    INDEX
    Explanations

    phrases after common words

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

    salt and pepper

    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
     milliamperes
    0.50
     gerçekten
    0.49
     rikt
    0.48
    ².
    0.47
     ayr
    0.46
     Ohm
    0.46
     önceki
    0.46
    ໂດ
    0.45
     rupp
    0.45
     υπάρχ
    0.45
    POSITIVE LOGITS
    thio
    0.47
     scathing
    0.45
     非
    0.44
     deepening
    0.44
     ಸಂಧಿ
    0.43
    chio
    0.43
    objective
    0.43
    игра
    0.43
     gripping
    0.42
    に残
    0.42
    Activations Density 0.000%

    No Known Activations