© 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. 31-GEMMASCOPE-2-RES-262K
    7. 82987
    Prev
    Next
    INDEX
    Explanations

    action vs happening

    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
    一场
    0.45
    が得
    0.45
    欬
    0.45
    ในการ
    0.44
    厘
    0.43
     Jésus
    0.43
    inflammatory
    0.41
    釐
    0.41
     зміни
    0.41
    étude
    0.40
    POSITIVE LOGITS
     blurring
    0.50
     district
    0.49
     worker
    0.49
    itelja
    0.46
    viation
    0.46
     credibility
    0.45
     dude
    0.44
     broader
    0.44
     gays
    0.44
     baz
    0.43
    Activations Density 0.003%

    No Known Activations