© 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. 220569
    Prev
    Next
    INDEX
    Explanations

    collars and tags

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

    Why? Because

    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
     ভোগের
    0.45
     或者
    0.44
    to
    0.41
     উত্তেজিত
    0.41
    قيقة
    0.41
     szkoły
    0.40
    াফিক
    0.40
    ἢ
    0.39
     Makan
    0.38
    ৃতা
    0.38
    POSITIVE LOGITS
    டுக்க
    0.48
     ปี
    0.48
    पर्यंत
    0.47
     مثل
    0.46
     poput
    0.45
    ปี
    0.44
     नवम्बर
    0.44
    冬
    0.43
    좁
    0.43
     nostrum
    0.42
    Activations Density 0.001%

    No Known Activations