© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 15266
    Prev
    Next
    INDEX
    Explanations

    property and license

    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
    ()+"
    0.91
    padă
    0.91
    __(/*!
    0.90
    åk
    0.90
    nilvadipine
    0.89
    Ⲣ
    0.86
    chanted
    0.85
    istatic
    0.85
    𝐦
    0.84
    Prothorax
    0.84
    POSITIVE LOGITS
     owner
    0.89
     first
    0.83
     on
    0.78
     owners
    0.77
     Meanwhile
    0.73
     sign
    0.71
     head
    0.71
     deserts
    0.70
     lad
    0.70
     Georgia
    0.70
    Activations Density 0.000%

    No Known Activations