© 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. 6396
    Prev
    Next
    INDEX
    Explanations

    numbers or s

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

    numbers and special tokens

    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
    ल्याण
    0.27
    éraires
    0.27
    铐
    0.26
    त्तीस
    0.25
    ätten
    0.25
    ट्टर
    0.25
     Monterey
    0.25
     spectrom
    0.24
     Horticultural
    0.24
     पर्व
    0.24
    POSITIVE LOGITS
    ;//
    0.29
     inorder
    0.29
    ;
    0.29
    ()(
    0.29
     )
    0.29
     maybe
    0.28
    …)
    0.28
    )?
    0.28
     tyle
    0.28
    <unused61>
    0.28
    Activations Density 0.096%

    No Known Activations