© 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. 14108
    Prev
    Next
    INDEX
    Explanations

    node

    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
     Боль
    1.66
    odim
    1.61
    ພັນ
    1.55
    陲
    1.49
    Боль
    1.49
    ᓛ
    1.47
     Kali
    1.46
    दरी
    1.45
    кай
    1.44
     Cac
    1.44
    POSITIVE LOGITS
     &
    3.56
     and
    3.40
    ＆
    3.31
     অ্যান্ড
    3.11
     \&
    3.10
    และ
    3.03
    &
    2.99
     và
    2.77
    &-
    2.76
     &/
    2.73
    Activations Density 1.872%

    No Known Activations