© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8846
    Prev
    Next
    INDEX
    Explanations

    recommendations and suggestions

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

    making recommendations

    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_40_width_16k_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
     ဂ
    0.36
    Syntax
    0.35
    DEFINE
    0.35
    webElement
    0.35
    퍼
    0.35
    Hope
    0.35
    DECLARE
    0.34
    ဿ
    0.34
     الفيزياء
    0.34
    queryParams
    0.34
    POSITIVE LOGITS
     recommendation
    3.25
     recommended
    3.14
    建议
    3.13
     recommendations
    3.09
    建議
    3.08
     recomend
    2.97
    recommend
    2.95
     recommend
    2.92
    推荐
    2.91
     Recommendation
    2.86
    Activations Density 0.779%

    No Known Activations