© 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. 6332
    Prev
    Next
    INDEX
    Explanations

    multiple languages and historical entities

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

    speeches about Narendra Modi

    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
    ']).
    0.38
    ')[
    0.37
    '}).
    0.37
    好き
    0.36
    '><
    0.36
    硬
    0.36
     Regions
    0.35
    వె
    0.35
     Visits
    0.35
     Beginn
    0.35
    POSITIVE LOGITS
     পোষ
    0.41
     proclaimed
    0.39
    สงค์
    0.38
    <0xCD>
    0.38
     तत्कालीन
    0.37
     notably
    0.37
     เฮ
    0.37
     proclaims
    0.36
     proportionally
    0.36
    achim
    0.36
    Activations Density 0.038%

    No Known Activations