© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30724
    Prev
    Next
    INDEX
    Explanations

    listing types of or examples

    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
    2
    0.75
    This
    0.68
    i
    0.68
    ();
    0.66
     were
    0.63
    Same
    0.62
     dites
    0.61
    can
    0.61
    Time
    0.60
    L
    0.59
    POSITIVE LOGITS
    也就是说
    0.70
    不仅
    0.59
    出
    0.59
    不僅
    0.57
     véritables
    0.57
    正是
    0.56
     এতটাই
    0.55
    的价格
    0.54
    éma
    0.54
    成
    0.52
    Activations Density 0.072%

    No Known Activations