© 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. 190718
    Prev
    Next
    INDEX
    Explanations

    even more

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

    keyword planner tool

    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
     descriptions
    0.46
     änd
    0.46
    ே
    0.44
     areas
    0.43
     altri
    0.43
    ти
    0.43
    дент
    0.42
     outros
    0.41
     sentencing
    0.41
    धनों
    0.41
    POSITIVE LOGITS
    اني
    0.52
    الية
    0.52
    اري
    0.50
     مجموعه
    0.48
    凜
    0.47
    niac
    0.46
    ributing
    0.46
     الأخ
    0.45
     cuire
    0.45
    おい
    0.45
    Activations Density 0.000%

    No Known Activations