© 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. 255117
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Министерства
    0.55
     نیرو
    0.50
    地の
    0.48
     ministry
    0.47
     கலங்கரை
    0.46
     министер
    0.46
     docentes
    0.46
    𓏧
    0.45
     تۆ
    0.45
     лабора
    0.44
    POSITIVE LOGITS
    clicking
    0.43
    的一切
    0.42
    ody
    0.40
     preciso
    0.40
    amount
    0.40
    centaje
    0.39
    reson
    0.38
     precum
    0.38
    Amount
    0.38
     sangre
    0.38
    Activations Density 0.000%

    No Known Activations