© 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. 105917
    Prev
    Next
    INDEX
    Explanations

    suit models

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

    types of data and scales

    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
    物品
    0.46
    坸
    0.46
    勂
    0.44
    䀘
    0.43
    儿童
    0.43
    但我
    0.42
     কিন্ত
    0.42
     showers
    0.42
    芢
    0.41
    开车
    0.41
    POSITIVE LOGITS
     Milit
    0.55
     Ceres
    0.53
    proper
    0.50
    plastic
    0.49
    phia
    0.47
    phase
    0.47
    の種類
    0.47
     IFS
    0.47
     Hạ
    0.47
    kaan
    0.46
    Activations Density 0.002%

    No Known Activations