© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1401
    Prev
    Next
    INDEX
    Explanations

    legal paragraph or category

    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
    apayati
    0.20
     Hän
    0.19
    それ
    0.19
    ه‌ها
    0.19
    उसके
    0.19
    ऐसे
    0.17
    $-$,
    0.17
    𝚆
    0.17
     അതിനാ
    0.17
    është
    0.17
    POSITIVE LOGITS
    0.26
    �
    0.22
    <0xC2>
    0.22
    <0xE2>
    0.21
    <0xF3>
    0.20
    </em>
    0.20
    ​
    0.19
    Â
    0.19
    <unused61>
    0.19
    <0xE3>
    0.19
    Activations Density 2.749%

    No Known Activations