© 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. 89577
    Prev
    Next
    INDEX
    Explanations

    the regulated market

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

    quadruped, adaptable, August

    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
    jera
    0.46
    ΰ
    0.46
    ର୍
    0.45
     campfire
    0.44
    štění
    0.44
     fireplace
    0.44
     způ
    0.43
     renter
    0.43
     hearth
    0.42
     হওয়ায়
    0.42
    POSITIVE LOGITS
    .
    0.61
    。
    0.52
    チン
    0.47
    ។
    0.46
    $.
    0.45
    Note
    0.43
    NOTE
    0.43
    \.
    0.42
    тивными
    0.42
     Sciences
    0.41
    Activations Density 0.000%

    No Known Activations