© 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. 18357
    Prev
    Next
    INDEX
    Explanations

    states or conditions

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

    regret or pedestrian actions

    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
    ag
    0.57
    habit
    0.56
    au
    0.51
     l
    0.51
     n
    0.50
     org
    0.48
     organiz
    0.48
    aber
    0.47
     c
    0.46
    gift
    0.46
    POSITIVE LOGITS
     RCLCPP
    0.53
    ция
    0.52
    દર
    0.51
    முடி
    0.51
    RUPTION
    0.49
     статистика
    0.49
     спи
    0.48
    эл
    0.48
     લઈ
    0.48
    CMAKE
    0.47
    Activations Density 0.000%

    No Known Activations