© 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. 6879
    Prev
    Next
    INDEX
    Explanations

    LaTeX, geometry, tikz, width

    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
    Duplicates
    0.77
    Sun
    0.77
    RequestBody
    0.77
    Same
    0.76
    Prop
    0.75
    me
    0.73
    ுற
    0.73
    n
    0.73
    Santa
    0.72
    Ist
    0.70
    POSITIVE LOGITS
    ЕЛЬ
    0.91
    olese
    0.90
     notifier
    0.89
     officielle
    0.88
     bố
    0.83
     Offic
    0.83
     officiel
    0.80
     Umum
    0.80
     piezo
    0.79
     CVT
    0.79
    Activations Density 0.001%

    No Known Activations