© 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. 22829
    Prev
    Next
    INDEX
    Explanations

    always on call

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

    digital wallets or pockets

    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
     empezar
    0.55
    ב
    0.54
     empiezan
    0.51
     각종
    0.50
    ॉर्ट
    0.50
    বঙ্গের
    0.50
     rẻ
    0.47
     Engineered
    0.47
    ب
    0.47
     pruebas
    0.47
    POSITIVE LOGITS
    vori
    0.45
    chenk
    0.44
    oge
    0.44
    agog
    0.44
    lblName
    0.44
    nika
    0.43
    älte
    0.43
    iden
    0.43
    eri
    0.43
    śli
    0.42
    Activations Density 0.000%

    No Known Activations