© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4938
    Prev
    Next
    INDEX
    Explanations

    lists features of property

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

    GitHub Copilot

    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
     நிகழ்ச்ச
    0.42
    ૉ
    0.42
    fully
    0.39
    苌
    0.39
     vaste
    0.37
    चक
    0.37
    जवळ
    0.37
     spesial
    0.37
     బె
    0.37
    嫋
    0.37
    POSITIVE LOGITS
    Intern
    0.54
     pertinent
    0.52
    .--
    0.49
     Intern
    0.48
     relevant
    0.46
     pertinente
    0.45
     thermo
    0.44
     Relevance
    0.43
     Cad
    0.43
    relevant
    0.42
    Activations Density 0.011%

    No Known Activations