© 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. 260765
    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
     בדי
    0.44
    เร
    0.44
     постоянно
    0.43
    䡃
    0.43
     ビタミン
    0.41
    държа
    0.41
    बाल
    0.41
    קו
    0.41
     레
    0.41
    轮回
    0.40
    POSITIVE LOGITS
     halos
    0.43
     wound
    0.42
     cultured
    0.42
    ੨
    0.41
     ersten
    0.41
     tactics
    0.41
     ends
    0.40
     mechanism
    0.40
    他是
    0.40
     prerog
    0.40
    Activations Density 0.000%

    No Known Activations