© 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. 1963
    Prev
    Next
    INDEX
    Explanations

    physical posture and movement

    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
     ​​
    1.12
    ​
    0.98
    ​​
    0.95
    ⁣
    0.95
     ​​​​
    0.91
    ‍
    0.89
    ​,
    0.88
     ​
    0.86
    <0x0D>
    0.84
    <0xC2>
    0.84
    POSITIVE LOGITS
     admirably
    1.28
     heartily
    1.18
     speedily
    1.15
     superbly
    1.14
     reluctantly
    1.13
     scarcely
    1.12
     tastefully
    1.09
     eloquently
    1.09
     comfortably
    1.08
     deftly
    1.08
    Activations Density 0.768%

    No Known Activations