© 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. 90103
    Prev
    Next
    INDEX
    Explanations

    states of being or actions

    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
     Kun
    0.44
     제시
    0.42
    층
    0.42
    는
    0.42
    ilem
    0.41
    硏
    0.41
    焔
    0.40
    📂
    0.40
    したら
    0.40
     русском
    0.39
    POSITIVE LOGITS
    il
    0.53
    itating
    0.50
     (\
    0.48
    ো
    0.48
     geometri
    0.47
    логи
    0.46
    ни
    0.46
    oc
    0.45
     Individ
    0.45
     Addition
    0.45
    Activations Density 0.001%

    No Known Activations