© 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. 33862
    Prev
    Next
    INDEX
    Explanations

    "than" or "in" or "Black"

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

    sports bra

    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
     και
    0.50
     és
    0.48
    缃
    0.47
     và
    0.47
     și
    0.46
    闂
    0.46
     и
    0.46
    }}<
    0.45
     và
    0.45
     maakt
    0.44
    POSITIVE LOGITS
     चैन
    0.45
    aughter
    0.43
    thane
    0.42
     ಮಾಹಿತ
    0.41
     संतु
    0.40
     सजा
    0.40
    után
    0.40
     किसानों
    0.40
    ว่าจะ
    0.40
    honey
    0.39
    Activations Density 0.000%

    No Known Activations