© 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. 17-GEMMASCOPE-2-RES-16K
    7. 585
    Prev
    Next
    INDEX
    Explanations

    number 1

    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_17_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
     soak
    1.04
     soaking
    1.01
     demokrat
    1.00
    谋
    1.00
    瑶
    0.99
     Soak
    0.97
     suede
    0.97
     Default
    0.95
     Davis
    0.95
    တွေ့
    0.94
    POSITIVE LOGITS
    1
    2.64
    １
    2.31
    ١
    2.10
    १
    2.05
    𝟏
    1.85
    ۱
    1.83
    𝟭
    1.79
    ១
    1.73
    ૧
    1.73
    ๑
    1.72
    Activations Density 1.899%

    No Known Activations