© 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. 239158
    Prev
    Next
    INDEX
    Explanations

    as the

    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
    ن
    0.51
     =-
    0.50
    Changing
    0.48
     Changing
    0.47
     decades
    0.47
    1
    0.46
    categories
    0.45
    changing
    0.45
     mainstream
    0.44
    Batt
    0.44
    POSITIVE LOGITS
    esinin
    0.54
    ትር
    0.53
     ক্রিকেট
    0.52
    υχ
    0.52
    EnglishMarks
    0.52
     호
    0.51
    公子
    0.50
    ெற்ற
    0.49
    encji
    0.48
     indiquant
    0.48
    Activations Density 0.002%

    No Known Activations