© 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. 159559
    Prev
    Next
    INDEX
    Explanations

    text types or descriptions

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

    called, aim, or, values, Males

    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
    وسیع
    0.47
    ϊ
    0.44
     parmi
    0.43
    plein
    0.43
    ką
    0.42
     cei
    0.42
     učen
    0.42
    uy
    0.42
    সিক
    0.41
     equipado
    0.41
    POSITIVE LOGITS
    ;?>
    0.47
     ناب
    0.46
    囊
    0.46
     бюджет
    0.46
     אין
    0.45
     trúc
    0.45
     syllables
    0.45
     మీకు
    0.44
     არს
    0.44
     بكم
    0.44
    Activations Density 0.002%

    No Known Activations