© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    just-in-time inventory and scheduling

    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
    
    1.93
    Collider
    1.93
    Kiza
    1.91
    敺
    1.82
    𝐴
    1.75
    BeerItem
    1.75
    Prothorax
    1.74
    
    1.73
    EndZ
    1.72
    Witness
    1.72
    POSITIVE LOGITS
    se
    1.58
    igen
    1.37
    iber
    1.34
    low
    1.32
    ishing
    1.29
     era
    1.27
     ing
    1.27
    seb
    1.25
    ibh
    1.23
    il
    1.23
    Activations Density 0.001%

    No Known Activations