© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 159255
    Prev
    Next
    INDEX
    Explanations

    place today

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

    Commands, stop, track

    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
    Mayo
    0.47
     ultimo
    0.46
    す
    0.45
    を受
    0.45
    ultimo
    0.45
    貿易
    0.45
    弗
    0.45
     último
    0.44
    arcs
    0.44
    最
    0.44
    POSITIVE LOGITS
     جوجل
    0.52
     carr
    0.49
     приро
    0.48
     прилага
    0.46
    nare
    0.46
     މި
    0.45
     enumerate
    0.45
     onClose
    0.45
     وګ
    0.45
     пользователь
    0.44
    Activations Density 0.001%

    No Known Activations