© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 6692
    Prev
    Next
    INDEX
    Explanations

    UUIDs and alphanumeric IDs

    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
    f
    0.83
    n
    0.80
    es
    0.77
    ej
    0.75
    h
    0.71
    k
    0.71
    she
    0.70
    cer
    0.70
    ç
    0.69
    g
    0.69
    POSITIVE LOGITS
     Applies
    0.95
     MediaPlayer
    0.83
     ABA
    0.83
     IVA
    0.83
    اہد
    0.82
     vét
    0.80
     sparsim
    0.80
     Respect
    0.79
     Alberta
    0.79
     Braves
    0.78
    Activations Density 0.010%

    No Known Activations