© 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. 251759
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

    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
     দিনাজ
    0.50
    ރ
    0.49
    वास्तव
    0.48
    ட்ஸ்
    0.48
    ගත
    0.47
    𝚇
    0.47
     தண்ண
    0.47
    நம்
    0.46
    बर
    0.46
     vistos
    0.46
    POSITIVE LOGITS
    m
    0.46
    -
    0.45
    ‐
    0.44
    ↵
    0.44
    r
    0.43
     feasibility
    0.43
    golf
    0.43
     turn
    0.43
     ihre
    0.42
     Sä
    0.42
    Activations Density 0.000%

    No Known Activations