© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12886
    Prev
    Next
    INDEX
    Explanations

    locations and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    describing attributes of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veldig
    0.61
    /
    0.60
     velmi
    0.57
     nagyon
    0.55
     Haft
    0.54
    szyst
    0.49
    mediately
    0.49
     viele
    0.48
     sehr
    0.48
    tene
    0.48
    POSITIVE LOGITS
    누
    0.47
    ರಿ
    0.44
     lawmaker
    0.44
    金
    0.44
    身影
    0.43
    ంపు
    0.43
    女
    0.42
    খ্যাত
    0.41
    밋
    0.41
    า
    0.41
    Activations Density 0.228%

    No Known Activations