© 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. 243061
    Prev
    Next
    INDEX
    Explanations

    20th Century

    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
     intermedia
    0.47
    intermedi
    0.46
    Kar
    0.46
    h
    0.46
    Powers
    0.45
    کر
    0.45
    荘
    0.44
     کوڈ
    0.44
    MPa
    0.43
    シュ
    0.43
    POSITIVE LOGITS
     给
    0.52
    竻
    0.51
    larımız
    0.49
     étab
    0.49
     více
    0.48
     Yao
    0.48
     jede
    0.48
    이죠
    0.46
     كلام
    0.46
    ร้อม
    0.46
    Activations Density 0.013%

    No Known Activations