© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    state of being occupied or undergoing

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

    sensitive topics like exploitation

    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
    變化
    0.42
     сыгра
    0.41
    变化
    0.40
    Changes
    0.37
     गुणा
    0.37
     ライン
    0.36
    軼
    0.36
    SKIP
    0.36
    ﹀
    0.36
     সফল
    0.36
    POSITIVE LOGITS
     sedang
    0.48
     busy
    0.47
     fragile
    0.45
     unarmed
    0.45
     delicate
    0.45
     hectic
    0.44
    危険
    0.43
     unprepared
    0.43
     pregnant
    0.43
     crowded
    0.43
    Activations Density 0.192%

    No Known Activations