© 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. 156948
    Prev
    Next
    INDEX
    Explanations

    name followed by colon

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

    word-word pairings

    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
    کرا
    0.52
    ただ
    0.48
    eryka
    0.47
     erano
    0.47
    an
    0.46
    泰国
    0.46
    {
    0.46
    கிழ
    0.45
    도
    0.45
    ICHIGAN
    0.45
    POSITIVE LOGITS
     保護
    0.51
     យើង
    0.48
     విషయం
    0.46
     предметов
    0.46
     మరింత
    0.46
     হারিয়ে
    0.45
     হওয়ার
    0.45
     পিছনে
    0.44
     refills
    0.44
     вой
    0.44
    Activations Density 0.001%

    No Known Activations