© 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. 647
    Prev
    Next
    INDEX
    Explanations

    how it works

    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
    i
    2.25
    a
    2.10
    ه
    1.90
    й
    1.79
    es
    1.76
    ו
    1.72
    া
    1.63
    u
    1.61
    м
    1.56
    에
    1.54
    POSITIVE LOGITS
    <unused14>
    2.02
     despite
    1.76
     fateful
    1.69
     notwithstanding
    1.63
     accompanies
    1.63
    𝘁
    1.63
    即使
    1.62
    就算是
    1.61
     precludes
    1.58
    即便
    1.57
    Activations Density 0.784%

    No Known Activations