© 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. 1979
    Prev
    Next
    INDEX
    Explanations

    www. URLs

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

    api and links

    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
    [multimodal]
    0.32
    কদের
    0.31
    amientos
    0.31
     মিলিয়ন
    0.30
    িকাংশ
    0.30
    Спољашње
    0.30
     বুঝতে
    0.30
    শ্চ
    0.29
    вают
    0.29
    তিকর
    0.29
    POSITIVE LOGITS
    db
    0.30
     vis
    0.29
     感
    0.29
    vis
    0.28
    Greeting
    0.27
     シ
    0.27
    r
    0.27
     }}{\
    0.27
    Vis
    0.27
     ア
    0.27
    Activations Density 0.146%

    No Known Activations