© 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. 73762
    Prev
    Next
    INDEX
    Explanations

    not reluctant to do something

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

    lists, how often

    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
     {\
    0.45
    📍
    0.42
     A
    0.42
     H
    0.40
     laatste
    0.40
     P
    0.40
     menentukan
    0.39
     fabricant
    0.39
     Friday
    0.39
     Chi
    0.38
    POSITIVE LOGITS
    収入
    0.54
    ುವ
    0.46
    സീ
    0.46
    წიფ
    0.45
     વિસ્તાર
    0.44
    níka
    0.44
    μη
    0.43
    codetest
    0.42
     SoaException
    0.42
     米
    0.42
    Activations Density 0.001%

    No Known Activations