© 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. 245277
    Prev
    Next
    INDEX
    Explanations

    listing things or talking about actions

    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
    尷
    0.48
    Silva
    0.46
    那一
    0.45
     הרבה
    0.43
    Doll
    0.42
    亚马逊
    0.42
    新年
    0.41
    惡
    0.40
    리
    0.40
    然後
    0.39
    POSITIVE LOGITS
     tomatoes
    0.52
     to
    0.51
     comenzar
    0.50
     currants
    0.50
    یل
    0.49
     ocupar
    0.49
    ِی
    0.48
     قوانین
    0.48
    ciones
    0.48
     sizes
    0.47
    Activations Density 0.001%

    No Known Activations