© 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. 5162
    Prev
    Next
    INDEX
    Explanations

    brands and companies

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

    tech names followed by definitions

    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
    挀
    0.32
    हर
    0.31
    によると
    0.30
    үз
    0.30
    《
    0.29
    ട
    0.29
    <unused2133>
    0.29
    बहु
    0.29
     pomoc
    0.29
     loopholes
    0.29
    POSITIVE LOGITS
    ®
    0.63
    ®,
    0.55
    及其
    0.55
    ians
    0.52
     Gölü
    0.49
    ™
    0.49
    ian
    0.48
     Ltd
    0.46
    本体
    0.46
    ™,
    0.45
    Activations Density 0.166%

    No Known Activations