© 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. 7475
    Prev
    Next
    INDEX
    Explanations

    under reducing

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

    end of code block

    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
     जरुर
    0.39
    િન
    0.39
    の場合は
    0.37
     dunque
    0.37
     можли
    0.37
     Inbetriebnahme
    0.36
     ज़रूर
    0.36
    "]="
    0.36
    除く
    0.36
     Fo
    0.35
    POSITIVE LOGITS
     .
    0.61
     .$
    0.54
     .(
    0.51
     `.
    0.47
     .-
    0.43
    cdot
    0.40
    ugía
    0.40
     //.
    0.40
    erder
    0.37
     .;
    0.36
    Activations Density 0.001%

    No Known Activations