© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167270
    Prev
    Next
    INDEX
    Explanations

    complex or unusual situations

    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_40_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
     était
    0.44
    kert
    0.44
    cado
    0.43
    涮
    0.43
     pensado
    0.43
     singolo
    0.42
    piro
    0.41
     fatto
    0.41
     घेतल्या
    0.41
    phi
    0.40
    POSITIVE LOGITS
     discontinuity
    0.41
    麟
    0.39
    起来
    0.38
    脚
    0.38
     Osbourne
    0.37
     species
    0.37
     edgecolor
    0.37
     charity
    0.37
     impetus
    0.36
     vertebrae
    0.36
    Activations Density 0.001%

    No Known Activations