© 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. 10526
    Prev
    Next
    INDEX
    Explanations

    edge, shape, and parts

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

    physical attributes and parts

    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
     μο
    0.45
    筺
    0.44
    লে
    0.43
    アウトドア
    0.43
    擰
    0.43
     十
    0.42
    登山
    0.42
     wheels
    0.42
    单
    0.41
     单
    0.41
    POSITIVE LOGITS
     heel
    0.60
     undercut
    0.52
    heel
    0.50
     edge
    0.48
     Heel
    0.48
     shoulders
    0.46
     tip
    0.46
     bulge
    0.46
     shoulder
    0.45
     notch
    0.45
    Activations Density 0.622%

    No Known Activations