© 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. 165965
    Prev
    Next
    INDEX
    Explanations

    news article topics

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

    concepts defining specific 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
    ংলার
    0.47
     preachers
    0.46
    णारा
    0.45
    远远
    0.45
     شيء
    0.45
    Ճ
    0.44
    碐
    0.44
    rzy
    0.43
    볕
    0.43
     গুণে
    0.43
    POSITIVE LOGITS
     Theorem
    0.55
    Theorem
    0.47
    theorem
    0.44
     lumped
    0.43
    AN
    0.42
    ga
    0.42
     thrust
    0.42
     ज़ि
    0.42
    Ons
    0.42
    ✒
    0.42
    Activations Density 0.001%

    No Known Activations