© 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. 10273
    Prev
    Next
    INDEX
    Explanations

    or

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

    or

    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
     üç
    0.44
     पुन्हा
    0.43
    ห
    0.41
    フィ
    0.41
     मध्य
    0.40
     سين
    0.40
     पूर्व
    0.39
     노
    0.39
    ੰਜ
    0.39
     카
    0.39
    POSITIVE LOGITS
     hoặc
    0.63
     nebo
    0.58
     alebo
    0.57
    或
    0.57
     или
    0.56
     અથવા
    0.55
    /
    0.54
     veya
    0.53
     లేదా
    0.53
     yoki
    0.53
    Activations Density 0.279%

    No Known Activations