© 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. 86733
    Prev
    Next
    INDEX
    Explanations

    symbols and designations

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

    isn't thinking

    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
    acles
    0.58
     среду
    0.52
    6
    0.52
    ຽງ
    0.50
    ᱗
    0.50
     остальные
    0.49
     जवान
    0.49
     Швейца
    0.48
    5
    0.48
     सैनिक
    0.48
    POSITIVE LOGITS
    í
    0.52
    InitTypeDef
    0.50
    drum
    0.45
     undetectable
    0.45
    drawLine
    0.44
     Richardson
    0.43
    缐
    0.43
    antera
    0.42
    nemidophorus
    0.41
     NSUInteger
    0.41
    Activations Density 0.001%

    No Known Activations