© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1032
    Prev
    Next
    INDEX
    Explanations

    numbers and simple arithmetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
     borderColor
    1.54
     hostility
    1.50
    <unused2148>
    1.46
     방
    1.41
     discriminant
    1.41
     reverence
    1.35
    <unused1950>
    1.35
     discretion
    1.35
     장
    1.33
     동
    1.33
    POSITIVE LOGITS
    気になる
    1.03
     деп
    1.02
    कहीं
    1.02
    含ま
    1.02
    वह
    1.01
     Renner
    0.98
    énom
    0.96
    あげ
    0.96
    0
    0.95
    かない
    0.93
    Activations Density 0.351%

    No Known Activations