© 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. 53-GEMMASCOPE-2-RES-65K
    7. 467
    Prev
    Next
    INDEX
    Explanations

    numbers with units or currency

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

    numerical measurements and units

    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_53_width_65k_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
    निटी
    0.42
    <unused83>
    0.41
    Flicky
    0.38
    ખ્ય
    0.38
    द्री
    0.38
    jaty
    0.38
    叡
    0.38
    <unused72>
    0.37
    <unused41>
    0.37
    េទ
    0.37
    POSITIVE LOGITS
    5
    0.79
    7
    0.70
    6
    0.66
    4
    0.65
    8
    0.65
    %
    0.63
    2
    0.63
    9
    0.63
    %,
    0.62
    3
    0.61
    Activations Density 0.198%

    No Known Activations