© 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. 3012
    Prev
    Next
    INDEX
    Explanations

    end of turn markers

    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
    Three
    0.71
    Caut
    0.68
    Four
    0.68
    센
    0.68
    Five
    0.66
    Amount
    0.64
    Correct
    0.63
    Sue
    0.63
    Please
    0.62
    Et
    0.60
    POSITIVE LOGITS
     IUnary
    0.78
    魑
    0.76
    aktan
    0.76
     kawaii
    0.73
     wchar
    0.72
     veniam
    0.72
     ካ
    0.71
    askets
    0.71
     Sturm
    0.70
     cuyos
    0.70
    Activations Density 0.096%

    No Known Activations