© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6124
    Prev
    Next
    INDEX
    Explanations

    numbered list item start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    的新
    0.78
    enske
    0.76
     Gunn
    0.74
     nových
    0.74
     நெ
    0.73
    ၢ
    0.70
    new
    0.70
     योग्यता
    0.70
     newline
    0.69
     Span
    0.68
    POSITIVE LOGITS
    정
    0.82
    Pretty
    0.69
    Depos
    0.68
    Submit
    0.67
    방
    0.66
     Pretty
    0.64
     depos
    0.64
     PDEs
    0.63
     раді
    0.62
     treated
    0.62
    Activations Density 0.035%

    No Known Activations