© 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. 126
    Prev
    Next
    INDEX
    Explanations

    career

    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
    s
    2.24
    sels
    2.21
    sch
    2.00
    sus
    2.00
    sons
    1.99
    sap
    1.93
    e
    1.93
    sens
    1.92
    sü
    1.89
    sz
    1.77
    POSITIVE LOGITS
     Может
    2.16
    <unused908>
    2.03
    IGO
    2.01
     就是
    2.00
     cPix
    1.98
    Blurred
    1.96
    计量
    1.96
     практически
    1.95
     intently
    1.94
     MEDIC
    1.94
    Activations Density 0.000%

    No Known Activations