© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5180
    Prev
    Next
    INDEX
    Explanations

    agreements made as of

    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_65k_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
    ли
    1.10
    Boundary
    1.08
    湳
    1.02
    behaved
    1.00
    Number
    1.00
    ले
    0.97
    এমন
    0.96
    லே
    0.96
    чете
    0.95
     heck
    0.94
    POSITIVE LOGITS
     (>
    0.92
     sustent
    0.86
     суток
    0.86
     investigator
    0.85
    োধন
    0.85
    ICATION
    0.84
     BTW
    0.83
     Squares
    0.83
     útiles
    0.82
     Transmission
    0.82
    Activations Density 0.006%

    No Known Activations