© 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. 97543
    Prev
    Next
    INDEX
    Explanations

    wanted some

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

    special definitions with colon

    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
    ани
    0.49
    dml
    0.46
     ហើយ
    0.45
    ۸
    0.45
    дм
    0.45
    出血
    0.44
    騇
    0.44
    ۶
    0.44
    咶
    0.44
     Конгрегация
    0.43
    POSITIVE LOGITS
     banking
    0.47
     mid
    0.45
     Bring
    0.44
     Gateway
    0.44
     Piper
    0.43
     minimum
    0.43
     Camping
    0.42
     camping
    0.42
     divest
    0.41
     F
    0.41
    Activations Density 0.000%

    No Known Activations