© 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. 70029
    Prev
    Next
    INDEX
    Explanations

    delivered with, arrive in, prepared to

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

    exciting . 😉

    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
    一般的な
    0.52
     동
    0.52
    趣味
    0.51
     기술
    0.47
     물론
    0.47
     주변
    0.46
    Vil
    0.46
     ಜನ
    0.45
    頂きました
    0.45
     ɔ
    0.45
    POSITIVE LOGITS
    यों
    0.43
     должна
    0.42
     assertEquals
    0.40
     KNOW
    0.40
    مة
    0.39
    不但
    0.39
    বাসী
    0.38
     disadvantaged
    0.38
     resultlist
    0.38
    اء
    0.38
    Activations Density 0.000%

    No Known Activations