© 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. 223963
    Prev
    Next
    INDEX
    Explanations

    multilingual diverse words

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

    application management

    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
     हल्ला
    0.50
    䨪
    0.46
    <unused5>
    0.46
     эл
    0.46
    зне
    0.44
     Caucasian
    0.43
     জায়গায়
    0.43
     শতা
    0.42
     uncomplicated
    0.42
    妒
    0.42
    POSITIVE LOGITS
    م
    0.51
    m
    0.50
    জির
    0.50
     Couleur
    0.49
    ويب
    0.47
    WebGL
    0.46
    Marg
    0.46
    Concurrency
    0.46
    How
    0.45
    Speaking
    0.45
    Activations Density 0.001%

    No Known Activations