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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1703
    Prev
    Next
    INDEX
    Explanations

    city and its surroundings

    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
    ي
    1.78
    i
    1.37
    ি
    0.95
    ێن
    0.92
    에
    0.90
    éu
    0.88
    ኔ
    0.86
    ி
    0.86
    al
    0.86
    מל
    0.86
    POSITIVE LOGITS
    scapes
    1.92
     dwellers
    1.68
    蜃
    1.68
    wide
    1.67
    隍
    1.58
     streets
    1.50
     governments
    1.46
     Slick
    1.42
    町村
    1.38
     metropolitan
    1.36
    Activations Density 0.154%

    No Known Activations