© 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. 45194
    Prev
    Next
    INDEX
    Explanations

    track my

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

    not * technicallynot necessarilynot a

    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
     أهل
    0.54
    bentuk
    0.53
    mlin
    0.52
     ambiguity
    0.49
    corper
    0.47
     escolas
    0.46
     assumes
    0.46
    ạ
    0.46
    ERRY
    0.45
    mour
    0.45
    POSITIVE LOGITS
    รี
    0.50
     ราคา
    0.50
     ট্রে
    0.49
     ストレ
    0.46
    شار
    0.46
     ซึ่ง
    0.46
    ที่สุด
    0.45
     จำกัด
    0.45
     preset
    0.45
     รี
    0.44
    Activations Density 0.001%

    No Known Activations