© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137134
    Prev
    Next
    INDEX
    Explanations

    action-oriented descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TextureData
    0.50
    хран
    0.50
     상수
    0.48
    恙
    0.48
    ли
    0.47
     функции
    0.47
    ్ర
    0.46
     যে
    0.45
    熵
    0.45
     precedente
    0.45
    POSITIVE LOGITS
     E
    0.43
     Rep
    0.42
     replies
    0.42
     Kamm
    0.42
     often
    0.41
     reports
    0.41
     ön
    0.41
     it
    0.41
     indoors
    0.40
     Southern
    0.40
    Activations Density 0.006%

    No Known Activations