© 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. 250873
    Prev
    Next
    INDEX
    Explanations

    friends

    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
     Basque
    0.50
    थन
    0.46
     राजांनी
    0.46
     woodwork
    0.44
     came
    0.44
    鰍
    0.44
    했다
    0.43
     stretched
    0.43
    ভাস
    0.43
     peripher
    0.43
    POSITIVE LOGITS
     развитие
    0.50
     lauf
    0.48
     વિશે
    0.47
     طيب
    0.46
     спорт
    0.45
     是
    0.45
    يه
    0.44
     halte
    0.44
    旲
    0.44
     モデル
    0.44
    Activations Density 0.001%

    No Known Activations