© 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. 143619
    Prev
    Next
    INDEX
    Explanations

    spaces and comfortable

    np_acts-logits-general · gemini-2.5-flash-lite

    organized chaos, interactive experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Token
    0.49
     భాష
    0.48
    Forward
    0.47
    字母
    0.46
    文字列
    0.46
    郵
    0.45
    TextView
    0.44
    Insider
    0.44
    语
    0.44
    Hint
    0.44
    POSITIVE LOGITS
     è
    0.66
     équipé
    0.62
     particules
    0.56
     वापरा
    0.55
     spéciaux
    0.55
     entièrement
    0.53
     ruang
    0.53
     είναι
    0.53
     extrêmement
    0.53
     équipée
    0.53
    Activations Density 0.000%

    No Known Activations