© 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. 134764
    Prev
    Next
    INDEX
    Explanations

    entered for

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

    unions, summer, when, silence, released

    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
     September
    0.50
     August
    0.48
     เยอะ
    0.47
     や
    0.47
    $
    0.42
     หลัก
    0.41
     ところ
    0.41
    ijos
    0.40
    ​
    0.40
    rm
    0.39
    POSITIVE LOGITS
    样式
    0.48
     osmotic
    0.45
    滤波器
    0.44
    ޟ
    0.44
    所有人
    0.43
    Celltype
    0.43
    кта
    0.43
    வ்வ
    0.43
    Prothorax
    0.43
     rescuers
    0.43
    Activations Density 0.000%

    No Known Activations