© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84020
    Prev
    Next
    INDEX
    Explanations

    static public const create link register

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    文獻
    -1.00
    pedal
    -0.95
    状況
    -0.93
     Schauspieler
    -0.91
     nostra
    -0.91
    aneity
    -0.90
    jacks
    -0.89
    ஔ
    -0.88
    每个
    -0.86
    各种
    -0.85
    POSITIVE LOGITS
    假如
    0.96
    шите
    0.96
    响起
    0.94
     кабе
    0.93
    ACION
    0.91
     escondido
    0.91
    ginate
    0.91
    ографи
    0.90
    ametric
    0.90
    SUCCEEDED
    0.90
    Activations Density 0.002%

    No Known Activations