© 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. 51549
    Prev
    Next
    INDEX
    Explanations

    Chinese idioms

    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
    了一个
    0.16
    ьте
    0.15
    珅
    0.15
     isEmpty
    0.15
    就会
    0.14
     అనేది
    0.14
    为一个
    0.14
     ఒక
    0.14
     isValid
    0.14
    了一個
    0.13
    POSITIVE LOGITS
    and
    0.18
    hire
    0.15
    hwa
    0.15
     ウェ
    0.15
    r
    0.15
    ag
    0.14
    oil
    0.14
    sh
    0.14
    at
    0.14
    it
    0.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.