© 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. 1640
    Prev
    Next
    INDEX
    Explanations

    numbers and magnitudes

    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
     seven
    0.99
     nine
    0.87
     ৪
    0.87
     ৩
    0.86
    three
    0.84
    seven
    0.84
    nine
    0.83
     ২২
    0.82
     six
    0.82
     साढ़े
    0.80
    POSITIVE LOGITS
     hundred
    1.17
     thousand
    1.08
    hundred
    0.96
     Hundred
    0.92
    0
    0.91
    ousand
    0.89
     हज़ार
    0.89
     hundreds
    0.89
    Hundred
    0.88
    ۰۰
    0.87
    Activations Density 0.989%

    No Known Activations