© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 164
    Prev
    Next
    INDEX
    Explanations

    learners and audience actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    ↵↵
    0.44
    Let
    0.41
    A
    0.40
    Table
    0.40
    Num
    0.40
    M
    0.39
    Index
    0.39
     இரண்டு
    0.38
    ).
    0.38
    B
    0.38
    POSITIVE LOGITS
     envisions
    0.79
     believes
    0.76
     wants
    0.76
     expects
    0.75
     recognizes
    0.75
     deems
    0.74
     undertook
    0.73
     understands
    0.73
     knows
    0.73
     acknowledges
    0.72
    Activations Density 0.734%

    No Known Activations