© 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. 49622
    Prev
    Next
    INDEX
    Explanations

    squinting with light or at things

    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
    f
    0.99
    is
    0.83
    fes
    0.73
    ف
    0.70
    lerine
    0.65
    fär
    0.65
    k
    0.65
    för
    0.64
    fie
    0.64
    al
    0.63
    POSITIVE LOGITS
     squint
    0.76
     мыш
    0.61
     intellectually
    0.60
     malicious
    0.57
     มัน
    0.57
    는
    0.57
     glycolysis
    0.56
     caliente
    0.56
    在那里
    0.56
     embezzlement
    0.55
    Activations Density 0.001%

    No Known Activations