© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3507
    Prev
    Next
    INDEX
    Explanations

    question, capital, name after this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    3.12
    。
    2.53
    ।
    2.42
    .**
    2.28
    .).
    2.05
    ."
    2.03
    .*
    1.93
    +.
    1.90
    ).
    1.86
    ።
    1.86
    POSITIVE LOGITS
     असून
    1.47
    [],
    1.09
    ようで
    1.07
     بنائیں
    1.03
    -,
    1.02
    !”,
    1.02
     _,
    1.02
    ?”,
    1.02
     असल्याने
    1.00
    $/,
    0.98
    Activations Density 1.091%

    No Known Activations