© 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. 54412
    Prev
    Next
    INDEX
    Explanations

    `i` loop counter

    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
    彫
    0.46
    ز
    0.44
    З
    0.43
     denoting
    0.42
    ಾಮ
    0.41
     fd
    0.41
    لاک
    0.41
     হওয়ায়
    0.41
    投资
    0.40
    println
    0.40
    POSITIVE LOGITS
    ₊
    0.42
    ij
    0.42
     Murad
    0.41
     Force
    0.40
     force
    0.40
     али
    0.40
     takeaways
    0.39
     Giang
    0.39
     kaik
    0.39
     Huffington
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.