© 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. 155909
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words

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

    it depends

    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
    as
    0.66
    п
    0.59
    s
    0.58
    т
    0.57
    of
    0.56
    k
    0.56
    anos
    0.52
    an
    0.52
    one
    0.52
    ти
    0.52
    POSITIVE LOGITS
    糺
    0.48
     Versand
    0.47
     كريم
    0.47
    蠶
    0.47
     gleich
    0.46
     zám
    0.46
     Première
    0.45
    ഷേ
    0.45
    جس
    0.44
    侙
    0.44
    Activations Density 0.000%

    No Known Activations