© 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. 256678
    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
     vín
    0.49
     imen
    0.47
    ใ
    0.46
    าค
    0.45
    ۣ
    0.45
    rias
    0.44
     sy
    0.44
     benzo
    0.44
    싯
    0.42
    เมล
    0.42
    POSITIVE LOGITS
    対象
    0.50
     ছিল
    0.49
    કર્
    0.46
     கவர்
    0.44
     বেশ
    0.43
    goers
    0.43
    හ
    0.43
     कि
    0.43
     могло
    0.43
    could
    0.42
    Activations Density 0.000%

    No Known Activations