© 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. 163749
    Prev
    Next
    INDEX
    Explanations

    words like `powers`, `dead`, `down`

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

    argument is to pee

    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
    こんな
    0.57
    жерела
    0.53
    运营
    0.52
     Temmuz
    0.52
    ৫
    0.52
    年月
    0.51
    ZIONE
    0.51
    ９
    0.50
    쿱
    0.49
     эксплуа
    0.48
    POSITIVE LOGITS
    ian
    0.69
    ly
    0.61
    ate
    0.59
    able
    0.58
    ite
    0.56
    ia
    0.54
    loin
    0.53
     pria
    0.52
    ments
    0.51
    ions
    0.50
    Activations Density 0.000%

    No Known Activations