© 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. 43866
    Prev
    Next
    INDEX
    Explanations

    ask anything

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

    ask me anything

    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
    这句话
    0.55
    insulated
    0.48
    ᓛ
    0.46
     contemplative
    0.45
     Dalai
    0.44
     विचारक
    0.44
    ssymb
    0.44
     बीएड
    0.43
    Centered
    0.43
    closeup
    0.43
    POSITIVE LOGITS
    常見
    0.48
    িতে
    0.48
    常用
    0.45
     然後
    0.45
    內的
    0.45
     選
    0.44
    内
    0.43
     加
    0.43
    主要的
    0.43
    內
    0.42
    Activations Density 0.000%

    No Known Activations