© 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. 241074
    Prev
    Next
    INDEX
    Explanations

    responsibility and roles

    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
     카메라
    0.53
    Breath
    0.51
    ayi
    0.49
    닉
    0.49
    iku
    0.48
     रैली
    0.48
    Yang
    0.47
     lag
    0.47
    Window
    0.46
    이제
    0.46
    POSITIVE LOGITS
    个
    0.48
    واز
    0.46
    قط
    0.43
     preclude
    0.42
    衙
    0.41
     Petersen
    0.41
     angesehen
    0.41
     Verantwortung
    0.40
    家长
    0.40
     Lehrer
    0.40
    Activations Density 0.001%

    No Known Activations