© 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. 14653
    Prev
    Next
    INDEX
    Explanations

    plural forms

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

    list formats options

    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
    ar
    0.78
    ام
    0.69
    жного
    0.68
    ast
    0.67
    ab
    0.66
     होईल
    0.65
    igrant
    0.65
    ل
    0.64
    ressive
    0.62
    тник
    0.62
    POSITIVE LOGITS
    s
    1.21
    ים
    1.19
    们
    1.14
    們
    1.04
    들은
    1.03
    들을
    1.03
    들과
    1.02
    ों
    1.00
    들도
    0.95
    وں
    0.95
    Activations Density 0.123%

    No Known Activations