© 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-262K
    7. 56831
    Prev
    Next
    INDEX
    Explanations

    avoiding actions/situations

    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
     судь
    0.53
    躓
    0.47
     учун
    0.46
     kỹ
    0.45
    絟
    0.45
    するための
    0.44
     subdue
    0.44
    足り
    0.44
     Trichodesmium
    0.43
     GP
    0.43
    POSITIVE LOGITS
    ו
    0.53
     coupling
    0.49
    Klik
    0.48
    Piano
    0.46
    ा
    0.46
     buildings
    0.45
    Ink
    0.45
     audio
    0.45
     layouts
    0.45
     boats
    0.44
    Activations Density 0.001%

    No Known Activations