© 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. 137411
    Prev
    Next
    INDEX
    Explanations

    sedated, quoted, refer to

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

    foreign language content

    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
    hlen
    0.50
    ar
    0.44
    。
    0.44
     that
    0.44
    can
    0.43
    any
    0.43
    bcc
    0.42
    ．
    0.42
       
    0.41
     reorganization
    0.41
    POSITIVE LOGITS
    表達
    0.54
     الكثير
    0.50
    ༥
    0.49
     fieles
    0.49
    不斷
    0.47
     بدور
    0.46
    វិធី
    0.46
     لكن
    0.45
     филосо
    0.45
     vrlo
    0.45
    Activations Density 0.000%

    No Known Activations