© 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. 9-GEMMASCOPE-2-RES-16K
    7. 99
    Prev
    Next
    INDEX
    Explanations

    for example

    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_9_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
    ة
    2.19
    ed
    1.75
    ित
    1.39
    ת
    1.38
    я
    1.24
    ть
    1.24
     fabricante
    1.21
    ০০০
    1.21
    es
    1.20
    ️
    1.20
    POSITIVE LOGITS
    erun
    1.86
     sake
    1.70
     purposes
    1.64
     reasons
    1.64
     example
    1.63
     instance
    1.59
    erunner
    1.57
    asmuch
    1.55
    geries
    1.48
     awhile
    1.46
    Activations Density 0.596%

    No Known Activations