© 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. 251101
    Prev
    Next
    INDEX
    Explanations

    specific following words

    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
    趼
    0.55
    浧
    0.54
     利
    0.49
    訸
    0.46
    ٹس
    0.45
     крупней
    0.45
    SaveChangesAsync
    0.44
    莧
    0.44
     stanie
    0.44
    يكل
    0.44
    POSITIVE LOGITS
    ette
    0.48
     बाई
    0.47
     giấc
    0.45
    reward
    0.44
    -
    0.44
     coupé
    0.44
    ‌.
    0.44
    bladder
    0.43
    person
    0.43
     rewarding
    0.43
    Activations Density 0.001%

    No Known Activations