© 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. 175458
    Prev
    Next
    INDEX
    Explanations

    similar and opposite words

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

    explaining complex 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
     crainte
    0.49
    čiti
    0.48
    ೂರು
    0.47
     ರೂ
    0.46
    peč
    0.45
    孱
    0.45
    orget
    0.44
    elser
    0.44
     merito
    0.44
    griffen
    0.44
    POSITIVE LOGITS
    /
    0.54
     Yangzhou
    0.40
    AbsolutePath
    0.39
     Geophysical
    0.39
     MDL
    0.39
    インタ
    0.39
     Geophys
    0.38
     MBE
    0.37
     ইন্ডাস্ট্র
    0.37
     Structural
    0.36
    Activations Density 0.001%

    No Known Activations