© 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. 89729
    Prev
    Next
    INDEX
    Explanations

    mailing lists

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

    features and qualities

    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
    ipedia
    0.51
    inc
    0.50
    ch
    0.49
    asing
    0.48
    C
    0.46
    霸
    0.46
    kill
    0.46
    obs
    0.45
     एकल
    0.45
    羅
    0.44
    POSITIVE LOGITS
     appell
    0.48
    芑
    0.46
    杫
    0.46
     adaptability
    0.45
    كلمنا
    0.43
    تباينه
    0.43
     adapta
    0.42
     allele
    0.41
    いろんな
    0.41
     Антон
    0.41
    Activations Density 0.000%

    No Known Activations