© 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. 90162
    Prev
    Next
    INDEX
    Explanations

    implementation, distribution, nature

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

    expression of consistency

    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
    骛
    0.48
    p
    0.46
     sensibly
    0.46
    設立
    0.45
    ングル
    0.43
    ప్‌
    0.43
    0.42
     go
    0.42
    仕
    0.42
     자리
    0.42
    POSITIVE LOGITS
     ಮಾಡಿದ್ದಾರೆ
    0.57
    łym
    0.49
     inhum
    0.48
    ilustración
    0.48
    isotropic
    0.48
     stinging
    0.47
    yatiti
    0.47
     शोषण
    0.46
    Caucasian
    0.46
    ಬಹುದು
    0.46
    Activations Density 0.000%

    No Known Activations