© 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. 2223
    Prev
    Next
    INDEX
    Explanations

    ready to proceed

    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
     NOT
    1.13
     НЕ
    1.06
     সাধারন
    1.04
    ”、“
    1.00
    !!!!!
    0.97
     NEEDS
    0.95
    "){
    0.94
    !!!"
    0.93
     MUST
    0.92
     др
    0.92
    POSITIVE LOGITS
    那我們
    1.24
    Speaker
    1.21
     microphones
    1.20
     그다음에
    1.15
     그러면은
    1.15
     그렇죠
    1.14
     today
    1.13
     speaking
    1.12
     tonight
    1.12
     millimeter
    1.12
    Activations Density 0.195%

    No Known Activations