© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    Instructional or explanatory text

    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
    y
    4.57
    u
    4.29
    in
    4.18
    a
    3.98
    t
    3.91
    ০
    3.89
    m
    3.84
    i
    3.83
    er
    3.83
    an
    3.79
    POSITIVE LOGITS
    infoHeader
    1.50
    ⓛ
    1.45
    了一
    1.40
    Най
    1.38
    durationType
    1.37
    Кто
    1.36
    それでは
    1.35
    ainte
    1.35
    clickView
    1.34
    АТ
    1.33
    Activations Density 0.947%

    No Known Activations