© 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. 79437
    Prev
    Next
    INDEX
    Explanations

    structural formatting and lists

    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
     dwRes
    0.44
    閑
    0.43
    🫣
    0.42
    BERGER
    0.42
     வேறு
    0.42
    angé
    0.41
     chutney
    0.41
     unwarrant
    0.41
     WIRE
    0.41
    홋
    0.41
    POSITIVE LOGITS
    libc
    0.50
    Integral
    0.49
    uncle
    0.48
    Uncle
    0.45
    pot
    0.45
    fiction
    0.44
    Firstly
    0.44
    poch
    0.44
    mz
    0.44
    purs
    0.43
    Activations Density 0.000%

    No Known Activations