© 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. 241855
    Prev
    Next
    INDEX
    Explanations

    speech act punctuation

    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
    "});
    0.54
     precludes
    0.52
     misalignment
    0.52
     wedge
    0.51
    ”?
    0.50
     erotic
    0.48
     Parker
    0.47
     প্রভৃতির
    0.47
     refractive
    0.47
     prevents
    0.46
    POSITIVE LOGITS
    举
    0.57
    戙
    0.52
    舉
    0.52
     كلم
    0.50
    规则
    0.50
    ВА
    0.47
    跟我
    0.46
    兕
    0.46
    وم
    0.46
     ثلاث
    0.46
    Activations Density 0.000%

    No Known Activations