© 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-262K
    7. 5206
    Prev
    Next
    INDEX
    Explanations

    BFFs, Muffin, Pantry, Patience, Mop, Bored, Slovak, USA

    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_262k_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
    0.44
    cknowled
    0.39
    in
    0.37
    e
    0.36
    s
    0.35
    ം
    0.35
    a
    0.35
    u
    0.33
    i
    0.32
    et
    0.32
    POSITIVE LOGITS
    обходимо
    0.61
    которые
    0.56
    oltre
    0.52
    spapers
    0.45
    riors
    0.42
    otros
    0.41
    ногда
    0.41
    retanto
    0.41
    ductory
    0.40
    ocurrency
    0.40
    Activations Density 0.469%

    No Known Activations