© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11004
    Prev
    Next
    INDEX
    Explanations

    thin or slim things

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

    thin, narrow, lean

    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
     Osc
    0.40
    ioni
    0.37
    尼亚克
    0.37
    ItemBackground
    0.36
    讣
    0.36
    缽
    0.36
    ந்தை
    0.36
     оформления
    0.35
    ARKS
    0.35
    瓮
    0.35
    POSITIVE LOGITS
     thin
    2.19
     Thin
    2.08
    Thin
    1.97
    thin
    1.95
     thinner
    1.87
    薄
    1.81
     thinning
    1.70
     薄
    1.55
     thinly
    1.47
    얇
    1.45
    Activations Density 0.184%

    No Known Activations