© 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. 22-GEMMASCOPE-2-RES-16K
    7. 535
    Prev
    Next
    INDEX
    Explanations

    runeborn, lightovert

    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_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
    folk
    0.66
     biv
    0.64
     menc
    0.62
     partic
    0.61
    e
    0.61
     вза
    0.59
    성
    0.59
     kom
    0.58
    -
    0.58
    sanitize
    0.58
    POSITIVE LOGITS
    owering
    0.83
    ilk
    0.83
    ürk
    0.80
    ucking
    0.79
    ield
    0.78
    illing
    0.78
    ournal
    0.77
    øg
    0.77
    ounds
    0.77
    ublic
    0.77
    Activations Density 0.355%

    No Known Activations