© 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. 8782
    Prev
    Next
    INDEX
    Explanations

    verbs and derived forms

    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
     zoos
    1.65
     geralmente
    1.53
     deceiving
    1.52
    ՝
    1.51
     goed
    1.48
     dik
    1.46
     fazer
    1.46
     spect
    1.45
     soorten
    1.43
     अस्पतालों
    1.43
    POSITIVE LOGITS
    ing
    3.42
    ed
    3.34
    oretically
    3.28
    ো
    3.25
    es
    3.22
    theless
    3.00
    יות
    2.95
    t
    2.94
    ted
    2.89
    taining
    2.87
    Activations Density 0.764%

    No Known Activations