© 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. 255168
    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
    ביל
    0.44
     nisu
    0.42
    *((
    0.42
     soundness
    0.41
    chinese
    0.41
    </b>
    0.40
    ませんので
    0.39
    睨
    0.39
    handel
    0.39
    DUC
    0.38
    POSITIVE LOGITS
    ដោយ
    0.53
    କୁ
    0.53
     инструмент
    0.52
     күн
    0.52
     FeCl
    0.52
     iron
    0.51
     цель
    0.51
     FK
    0.51
     পুনর্ব
    0.50
     đảo
    0.50
    Activations Density 0.000%

    No Known Activations