© 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. 196806
    Prev
    Next
    INDEX
    Explanations

    pest-free environment and portable headlight

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

    building blocks of proteins

    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
    ಾನ್
    0.49
    另外
    0.49
    存款
    0.48
    fak
    0.45
     যোগদান
    0.44
     التحكم
    0.44
    ล
    0.43
    ranked
    0.43
    ገኛ
    0.43
    更多的
    0.43
    POSITIVE LOGITS
     cuestión
    0.51
     N
    0.50
     `'\\
    0.49
     menulis
    0.48
     suger
    0.47
    реза
    0.47
     solicitud
    0.46
    oks
    0.46
    прос
    0.46
     solucion
    0.46
    Activations Density 0.000%

    No Known Activations