© 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. 158227
    Prev
    Next
    INDEX
    Explanations

    dual ports, birth, products, abound

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

    content generation guidance

    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
    عان
    0.51
    ని
    0.45
    <()>
    0.44
     toDo
    0.42
     inappropriately
    0.42
    летов
    0.41
     invertebrate
    0.41
     हानिकारक
    0.40
     bó
    0.40
     заинтересо
    0.40
    POSITIVE LOGITS
     trasform
    0.54
    9
    0.51
    ਮ
    0.49
     οικονομ
    0.49
     αυτό
    0.48
    verick
    0.47
     ততক্ষণ
    0.46
    onym
    0.46
    ihan
    0.46
    ukur
    0.45
    Activations Density 0.001%

    No Known Activations