© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 64244
    Prev
    Next
    INDEX
    Explanations

    structured phrases

    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_65k_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
     Sub
    0.39
     feu
    0.39
    response
    0.38
    ၎င်း
    0.38
     question
    0.37
    ).
    0.37
    ring
    0.37
    с
    0.37
    ようです
    0.36
    $,
    0.36
    POSITIVE LOGITS
    FINISHED
    0.56
    Sebagai
    0.52
     patrimoine
    0.52
    Valor
    0.49
    awsze
    0.48
    rado
    0.48
     Saltar
    0.48
     стиль
    0.47
    𒆜
    0.46
     everytime
    0.46
    Activations Density 0.018%

    No Known Activations