© 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. 58753
    Prev
    Next
    INDEX
    Explanations

    finally we, every angler

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

    new concepts or states

    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
    翹
    0.45
     swelling
    0.42
     forbearance
    0.41
     footprints
    0.40
    不由
    0.40
     الاستفهام
    0.40
    擔
    0.40
     irritability
    0.40
    估
    0.40
     exerting
    0.39
    POSITIVE LOGITS
     новое
    0.59
     جدید
    0.57
    stes
    0.52
     accompagné
    0.50
     новую
    0.50
    nieuw
    0.50
     nuevo
    0.49
     nuovo
    0.49
    зить
    0.48
    পদার্থ
    0.48
    Activations Density 0.000%

    No Known Activations