© 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. 2812
    Prev
    Next
    INDEX
    Explanations

    specific entities and categories

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

    the official or specific technical entity

    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
    );\
    0.44
     handels
    0.43
     territo
    0.42
    <unused2125>
    0.42
    __);
    0.41
    の中心
    0.41
     fontos
    0.41
    Several
    0.41
    不但
    0.41
    |<\
    0.40
    POSITIVE LOGITS
     latest
    0.66
     UK
    0.63
     infamous
    0.63
     NYU
    0.63
     Classic
    0.62
     BBC
    0.62
     Harvard
    0.61
     original
    0.60
     R
    0.59
     April
    0.59
    Activations Density 0.823%

    No Known Activations