© 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. 406
    Prev
    Next
    INDEX
    Explanations

    boxed final answer

    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
     seh
    1.55
     exager
    1.54
     ASGI
    1.45
    мана
    1.45
    <0x8D>
    1.42
    ِد
    1.40
     pushedAt
    1.39
    mittent
    1.39
     warme
    1.39
     শুন
    1.38
    POSITIVE LOGITS
     G
    1.11
    1.02
    imp
    1.01
    Run
    0.99
     V
    0.99
    Philipp
    0.99
    Acc
    0.98
    τισ
    0.98
     K
    0.96
    CH
    0.93
    Activations Density 0.029%

    No Known Activations