© 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. 86283
    Prev
    Next
    INDEX
    Explanations

    IMPROVEMENTS OR CHANGES

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

    poultry worksheet terms

    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
    вання
    0.49
     paroi
    0.48
     prohibitions
    0.47
    льне
    0.46
     accommodating
    0.46
     distint
    0.46
     ریز
    0.46
    )]),
    0.45
     undisclosed
    0.44
     walls
    0.44
    POSITIVE LOGITS
    Ꮁ
    0.57
    也就是
    0.54
    𝙵
    0.51
    Боль
    0.50
    Ꮲ
    0.50
    佟
    0.49
    Pretty
    0.47
    ड्र
    0.47
    广播
    0.46
    钲
    0.46
    Activations Density 0.000%

    No Known Activations