© 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. 247996
    Prev
    Next
    INDEX
    Explanations

    annually, Chapter Board, licensees

    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
    ╾
    0.49
    ض
    0.47
    upa
    0.46
    ется
    0.45
    けて
    0.45
    썹
    0.44
     offenders
    0.44
     законодав
    0.42
     tweepy
    0.42
    躹
    0.42
    POSITIVE LOGITS
    lari
    0.51
    ﺔ
    0.50
    lair
    0.49
    language
    0.48
    luft
    0.48
    VOR
    0.48
    دخل
    0.47
     هەر
    0.46
    t
    0.46
    l
    0.46
    Activations Density 0.000%

    No Known Activations