© 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. 51207
    Prev
    Next
    INDEX
    Explanations

    hardware specifications

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

    roles and responsibilities

    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
    Du
    0.51
    নে
    0.49
    नाथ
    0.48
    Ни
    0.47
    োর্ট
    0.46
    Ter
    0.46
    ో
    0.46
     académ
    0.46
    ுகளை
    0.46
    ４
    0.46
    POSITIVE LOGITS
     Bands
    0.47
     Ask
    0.47
     Kind
    0.46
     المقص
    0.45
     podmín
    0.45
     zuvor
    0.44
     Satz
    0.43
     verloren
    0.43
     ដ
    0.42
     Lö
    0.42
    Activations Density 0.000%

    No Known Activations