© 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. 2825
    Prev
    Next
    INDEX
    Explanations

    Cl or average

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

    key improvements and explanations

    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
     Lorem
    0.34
     you
    0.34
     reporters
    0.34
    you
    0.32
    কত
    0.31
     youre
    0.31
    <html>
    0.31
     MERCHANT
    0.31
     info
    0.31
     여기에
    0.31
    POSITIVE LOGITS
    നായ
    0.42
    UnderWater
    0.40
    ด
    0.40
    ческого
    0.38
     রস
    0.37
    ׄ
    0.37
    ærk
    0.37
     puriso
    0.36
    rasında
    0.36
    ಕ್ರ
    0.36
    Activations Density 0.068%

    No Known Activations