© 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. 14466
    Prev
    Next
    INDEX
    Explanations

    existentialism and existentialists

    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
     Grass
    1.08
    주일
    1.02
    翱
    0.97
     گز
    0.97
     والق
    0.97
    カラ
    0.96
    縮
    0.95
     genommen
    0.95
    raff
    0.93
     バー
    0.92
    POSITIVE LOGITS
     keenly
    1.27
     inherently
    1.26
     ständig
    1.19
    kräfte
    1.18
     stubbornly
    1.17
     decisively
    1.15
     unethical
    1.13
     sabía
    1.12
     desperately
    1.12
    ::_
    1.11
    Activations Density 0.510%

    No Known Activations