© 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. 2664
    Prev
    Next
    INDEX
    Explanations

    compound surnames in names

    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
     Infl
    0.52
     Meat
    0.50
     tractable
    0.48
    Meat
    0.47
     ин
    0.46
    ಿಸಿದ
    0.46
     대하여
    0.46
    또
    0.46
     Calcul
    0.46
     நூற்ற
    0.45
    POSITIVE LOGITS
    era
    0.66
    stone
    0.66
    ani
    0.65
    ova
    0.64
    ila
    0.64
    ätter
    0.63
    arlight
    0.63
    wood
    0.62
    spring
    0.62
    aker
    0.62
    Activations Density 0.015%

    No Known Activations