© 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. 2730
    Prev
    Next
    INDEX
    Explanations

    text following "this"

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

    factual questions

    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
    棹
    0.35
    tble
    0.35
     بالټ
    0.35
    ኬ
    0.35
    Databaze
    0.34
     rétréci
    0.34
    supportsFocus
    0.34
    CurrentImageData
    0.34
    햅
    0.34
    <unused33>
    0.33
    POSITIVE LOGITS
    ...
    0.42
     օ
    0.37
    Sp
    0.36
    ..."
    0.35
    **)
    0.34
    ...”
    0.34
     (*
    0.33
    </h1>
    0.32
    <0xE2>
    0.32
     (?
    0.32
    Activations Density 0.183%

    No Known Activations