© 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
    2. Gemma-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 4051
    Prev
    Next
    INDEX
    Explanations

    crisis text line number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proceed
    0.83
    cript
    0.79
    िवा
    0.78
    proceed
    0.77
     Proceed
    0.77
    l
    0.75
    lush
    0.73
    たら
    0.72
    ohol
    0.70
    che
    0.70
    POSITIVE LOGITS
    myButtons
    0.75
     interesting
    0.74
    ቈ
    0.74
    ኵ
    0.73
    пок
    0.72
    <unused458>
    0.71
     merino
    0.71
    BCD
    0.71
    badges
    0.71
     calyc
    0.70
    Activations Density 0.016%

    No Known Activations