© 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. 136
    Prev
    Next
    INDEX
    Explanations

    introducing explanations or conclusions

    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
     "
    1.47
    ,
    1.34
     及
    1.29
     -
    1.26
     /
    1.25
     or
    1.23
     餐
    1.22
     (
    1.22
     '
    1.20
    1.19
    POSITIVE LOGITS
    There
    2.48
    Basically
    2.34
    Perhaps
    2.33
    They
    2.28
    Saya
    2.24
    Everyone
    2.23
    Every
    2.23
    If
    2.22
    It
    2.21
    We
    2.20
    Activations Density 0.841%

    No Known Activations