© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 145082
    Prev
    Next
    INDEX
    Explanations

    prompts starting with Square

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     الن
    0.63
     på
    0.55
     mä
    0.55
     კ
    0.53
     الص
    0.52
     تص
    0.52
     tə
    0.52
     kä
    0.50
     ø
    0.50
     hø
    0.50
    POSITIVE LOGITS
    S
    0.65
    ნა
    0.63
    <unused242>
    0.58
    らない
    0.57
    いる
    0.57
    нее
    0.57
    stant
    0.57
    களை
    0.57
    িনি
    0.56
    פ
    0.56
    Activations Density 0.002%

    No Known Activations