© 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. 202320
    Prev
    Next
    INDEX
    Explanations

    numbers followed by unit

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

    Highlands, object, reason

    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
    ਹਾ
    0.47
    當時
    0.46
    當年
    0.45
    傘
    0.45
     xác
    0.44
    рев
    0.44
    َان
    0.44
    MARKS
    0.44
    襪
    0.43
    規定
    0.43
    POSITIVE LOGITS
     ریز
    0.48
     بنابراین
    0.47
     cosm
    0.47
     وسی
    0.44
     enthr
    0.44
     تحصیل
    0.43
     กลุ่ม
    0.42
    یل
    0.42
     graphene
    0.41
     homic
    0.41
    Activations Density 0.000%

    No Known Activations