© 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. 121474
    Prev
    Next
    INDEX
    Explanations

    classifying into categories

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

    lists, descriptions, data formats

    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
     systemat
    0.44
     obowią
    0.42
    ̄
    0.42
     świat
    0.41
     względu
    0.41
     ardent
    0.41
     Dole
    0.41
     toàn
    0.40
     bl
    0.39
     plaf
    0.39
    POSITIVE LOGITS
    ტი
    0.59
    us
    0.47
    genres
    0.46
    ᱔
    0.46
    genre
    0.46
    ucidation
    0.46
    िफ
    0.45
    rakech
    0.45
    ده
    0.44
    isations
    0.44
    Activations Density 0.001%

    No Known Activations