© 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. 1736
    Prev
    Next
    INDEX
    Explanations

    products and media titles

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

    urls and paths

    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
    தூ
    0.25
     tranquilo
    0.25
     traité
    0.24
    څ
    0.24
     തൂ
    0.23
    欬
    0.23
     ligado
    0.23
     headspace
    0.23
     tratado
    0.23
    গানি
    0.23
    POSITIVE LOGITS
    tr
    0.25
    movies
    0.24
    Subjects
    0.23
    Movies
    0.23
    <0x0D>
    0.22
    ir
    0.22
    workflows
    0.22
    EM
    0.22
    new
    0.22
    acceler
    0.22
    Activations Density 0.496%

    No Known Activations