© 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. 7914
    Prev
    Next
    INDEX
    Explanations

    scientific notation

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

    scientific notation with x or ×

    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
    脚步
    0.47
    চৈত
    0.43
    Დ
    0.42
    मिटेड
    0.42
     কারাগ
    0.42
     всему
    0.41
    䐂
    0.40
    বির
    0.40
     бир
    0.40
    कोड
    0.40
    POSITIVE LOGITS
     ×
    0.98
    ×
    0.93
     trillion
    0.67
     billion
    0.66
    
    0.65
     million
    0.64
     milion
    0.61
     x
    0.60
    ⨯
    0.60
     exponent
    0.58
    Activations Density 0.010%

    No Known Activations