© 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-16K
    7. 7526
    Prev
    Next
    INDEX
    Explanations

    locations and points of reference

    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
    intérieur
    0.80
    ряз
    0.77
     Interiors
    0.74
    細かい
    0.72
     sytu
    0.72
    斕
    0.72
    interior
    0.72
     pendent
    0.71
    方面的
    0.69
     뒷
    0.69
    POSITIVE LOGITS
     entrance
    1.07
     entrances
    1.07
     where
    1.06
     equator
    0.95
     exits
    0.92
    Exit
    0.88
     જ્યાં
    0.88
    Where
    0.88
     exit
    0.88
     axis
    0.87
    Activations Density 0.167%

    No Known Activations