© 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. 2020
    Prev
    Next
    INDEX
    Explanations

    multiplication and dimensions

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

    multiplication symbol and concept

    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
    습니까
    0.44
    ದಯ
    0.43
     करीत
    0.40
    เคย
    0.39
    ❛
    0.39
    ނީ
    0.39
    蕨
    0.39
    一度
    0.38
    <unused21>
    0.38
    prone
    0.38
    POSITIVE LOGITS
     cm
    0.54
     magnification
    0.48
     whatever
    0.45
    高さ
    0.45
     multiplier
    0.44
     height
    0.43
     times
    0.42
    ×
    0.42
     (
    0.41
     redundancy
    0.39
    Activations Density 0.108%

    No Known Activations