© 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. 259225
    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
     последова
    0.47
     attualmente
    0.46
     aqui
    0.45
    pieza
    0.45
     interno
    0.44
    س
    0.44
     profunda
    0.44
     actualmente
    0.43
     Nodo
    0.43
     मझ
    0.42
    POSITIVE LOGITS
    FreeBuf
    0.45
    ৎকার
    0.44
    ↵↵↵↵
    0.41
     নয়
    0.39
    吗
    0.39
    誣
    0.39
    事先
    0.39
    诬
    0.38
     retali
    0.38
     스포츠
    0.38
    Activations Density 0.002%

    No Known Activations