© 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. 47587
    Prev
    Next
    INDEX
    Explanations

    oxtail soup, million, March, PRO

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

    specific actions and technical terms

    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
    innen
    0.51
    isso
    0.48
    ientôt
    0.48
    ilos
    0.48
    lette
    0.47
    ersch
    0.46
    瀟
    0.46
    ino
    0.46
    isches
    0.46
    essler
    0.46
    POSITIVE LOGITS
    кри
    0.50
    멕
    0.49
    וק
    0.48
    키
    0.48
    ゲ
    0.47
     Okamoto
    0.46
     nominated
    0.45
    構造
    0.45
    げ
    0.45
    جه
    0.44
    Activations Density 0.000%

    No Known Activations