© 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. 212854
    Prev
    Next
    INDEX
    Explanations

    currency exchange or statistics

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

    trial with / cluttered with

    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
    бот
    0.49
    쟌
    0.47
     Activities
    0.47
     Conc
    0.46
     요즘
    0.46
    ４
    0.45
     ACTIVITIES
    0.45
     최근
    0.45
    르
    0.44
    ຄວ
    0.43
    POSITIVE LOGITS
     admiss
    0.45
     ബന്ധ
    0.44
     banging
    0.42
     corp
    0.41
    ie
    0.39
    agian
    0.39
     মানব
    0.39
     scrimmage
    0.39
     whistleblower
    0.38
    una
    0.38
    Activations Density 0.001%

    No Known Activations