© 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. 3811
    Prev
    Next
    INDEX
    Explanations

    voter ID number

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

    effort, impact, funny, probability, level

    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
    न्दावन
    0.45
    BtnFill
    0.41
    সময়
    0.41
    ংলার
    0.39
    ଢ
    0.38
    ক্ষণের
    0.38
    صیٰ
    0.37
    সময়
    0.37
    Πα
    0.37
    ஞ்ஞான
    0.36
    POSITIVE LOGITS
    <strong>
    0.46
    +
    0.46
     idem
    0.41
     ​​​​
    0.41
    ื
    0.40
    (?)
    0.39
    <b>
    0.39
     ,
    0.38
    inist
    0.38
     Kear
    0.38
    Activations Density 0.327%

    No Known Activations