© 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. 223432
    Prev
    Next
    INDEX
    Explanations

    pinyin and numbers in brackets

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

    Racing Club

    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
     Bernstein
    0.44
     bet
    0.43
    इका
    0.41
     XVIII
    0.40
     spectre
    0.39
    рены
    0.39
    <h4>
    0.38
    β
    0.38
    ве
    0.38
     tendre
    0.38
    POSITIVE LOGITS
    ulants
    0.44
     Solubility
    0.43
     रोजाना
    0.40
    Miles
    0.38
    มาชิก
    0.38
    แส
    0.38
    Fecha
    0.38
     যতই
    0.38
     $<\
    0.37
     મેળ
    0.37
    Activations Density 0.001%

    No Known Activations