© 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. 31-GEMMASCOPE-2-RES-262K
    7. 204213
    Prev
    Next
    INDEX
    Explanations

    lactose, days, Windows, PN, &&

    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_31_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
    ld
    0.56
     çıkar
    0.52
     October
    0.50
     afet
    0.50
     Ocak
    0.50
    ต
    0.50
    গ্
    0.49
    tki
    0.48
    𒐪
    0.48
    gal
    0.47
    POSITIVE LOGITS
     Inches
    0.43
     বিজনেস
    0.41
     milliliters
    0.41
    netHex
    0.41
     scallops
    0.41
    Residual
    0.39
     осигурање
    0.39
     Adequate
    0.39
     inches
    0.38
     розта
    0.38
    Activations Density 0.001%

    No Known Activations