© 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. 7-GEMMASCOPE-2-RES-16K
    7. 256
    Prev
    Next
    INDEX
    Explanations

    section headers or numbered lists

    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_7_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
    ératures
    1.54
    '
    1.53
    holz
    1.50
     পূর্বা
    1.45
    чо
    1.44
    Meanwhile
    1.42
    Además
    1.40
    Hard
    1.39
    êmio
    1.38
    Now
    1.38
    POSITIVE LOGITS
    <unused2221>
    1.55
     kuten
    1.46
    <unused508>
    1.43
    しゃれ
    1.42
     menstru
    1.41
    <unused1830>
    1.41
     แม
    1.41
    AnimationStyle
    1.41
     pubescence
    1.40
    <unused1796>
    1.39
    Activations Density 0.337%

    No Known Activations