© 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. 130953
    Prev
    Next
    INDEX
    Explanations

    weather conditions

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

    NOT, Differences, father, language

    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
    um
    0.52
    size
    0.52
     it
    0.51
    ta
    0.50
    ilo
    0.49
    on
    0.48
    beri
    0.48
    %",
    0.47
    umis
    0.47
    tt
    0.47
    POSITIVE LOGITS
    ミックス
    0.54
    丈夫
    0.50
    民族
    0.50
    登
    0.50
    混合
    0.47
    ক্রমে
    0.47
    昔
    0.46
    STRUCTURE
    0.45
    ซิต
    0.44
    ชาว
    0.44
    Activations Density 0.001%

    No Known Activations