© 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. 179397
    Prev
    Next
    INDEX
    Explanations

    locations, services, and alerts

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

    Sector, Development, Lazy, Call, https

    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
    analyse
    0.47
    pump
    0.47
    碉
    0.46
    ಾಯಿ
    0.46
    sampling
    0.46
     သိ
    0.46
    classed
    0.45
    戤
    0.45
    镓
    0.44
    eds
    0.43
    POSITIVE LOGITS
     Aspect
    0.54
     Тре
    0.49
     इट
    0.48
     PowerShell
    0.48
     утром
    0.47
     ASUS
    0.47
     Grazie
    0.47
    ニック
    0.46
    ませ
    0.46
     Respons
    0.45
    Activations Density 0.000%

    No Known Activations