© 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. 22-GEMMASCOPE-2-RES-16K
    7. 83
    Prev
    Next
    INDEX
    Explanations

    forward slash after com or J

    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_22_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
     nämlich
    0.89
     တော့
    0.89
     yeah
    0.84
     totiž
    0.84
    pady
    0.84
     ちゃっ
    0.82
    ᱝ
    0.81
    േഷന്‍
    0.81
    ᅨ
    0.80
    стіше
    0.80
    POSITIVE LOGITS
    /
    5.18
     /
    4.26
    /(
    3.96
    /,
    3.89
    ／
    3.86
    /.
    3.74
    -/
    3.73
    /"
    3.70
    /{
    3.55
    /[
    3.52
    Activations Density 2.506%

    No Known Activations