© 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. 173645
    Prev
    Next
    INDEX
    Explanations

    preserving our choice

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

    code, conditions, or events

    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
    ۶
    0.57
    ６
    0.50
    專業
    0.49
    我們
    0.49
    专业
    0.48
    六
    0.48
    系列
    0.48
    质
    0.47
     Accompl
    0.46
    歷
    0.46
    POSITIVE LOGITS
    enchymal
    0.47
    "]},
    0.44
     Greenfield
    0.44
     swayed
    0.43
     ながら
    0.42
     sandy
    0.42
    AfterTax
    0.42
     ponder
    0.42
     сигнал
    0.42
     customs
    0.41
    Activations Density 0.000%

    No Known Activations