© 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. 128224
    Prev
    Next
    INDEX
    Explanations

    belief, control, feel, important, promotional

    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
    帮
    0.46
    Where
    0.46
    说
    0.45
    现实
    0.45
    信仰
    0.44
    可能
    0.44
    缺
    0.44
    Industrial
    0.43
    會
    0.43
    是一家
    0.43
    POSITIVE LOGITS
    %);
    0.47
    ytuc
    0.44
     centering
    0.43
    étique
    0.43
     tritium
    0.42
     alcohols
    0.42
    ahay
    0.42
     clouds
    0.42
    elere
    0.41
     neodymium
    0.40
    Activations Density 0.008%

    No Known Activations