© 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. 237518
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency, Tennis, card

    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
     அடுத்த
    0.55
    램
    0.46
     அதே
    0.46
     abundances
    0.46
    ப்பட்டு
    0.44
    라운
    0.44
     کاب
    0.43
     biosynthesis
    0.43
     установки
    0.43
     newsc
    0.43
    POSITIVE LOGITS
     gust
    0.46
     då
    0.45
    dig
    0.45
    の種類
    0.45
    試
    0.45
     takže
    0.43
    t
    0.43
    Col
    0.42
    digit
    0.42
     digit
    0.42
    Activations Density 0.001%

    No Known Activations