© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11840
    Prev
    Next
    INDEX
    Explanations

    errazketa eta errazketak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
     グレー
    0.69
     シルバー
    0.68
     L
    0.67
     Women
    0.67
     その他
    0.66
     リ
    0.65
     レディース
    0.64
     ホワイト
    0.64
     Water
    0.63
     Institute
    0.63
    POSITIVE LOGITS
    owlapi
    0.73
    sigmaf
    0.71
    shapeColor
    0.65
     সম্বন্ধে
    0.63
     permiss
    0.63
     þei
    0.63
     tolerances
    0.61
    वृद्धि
    0.60
    धारणा
    0.59
    <unused1248>
    0.59
    Activations Density 0.000%

    No Known Activations