© 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. 149541
    Prev
    Next
    INDEX
    Explanations

    prepared to continue

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

    testing boundaries and consequences

    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
    附
    0.50
     最后
    0.49
    员
    0.48
    还
    0.47
    我们
    0.45
    SuppressLint
    0.45
    最后
    0.45
    用
    0.44
    然后
    0.43
    लिंग
    0.43
    POSITIVE LOGITS
     whispered
    0.54
    窓
    0.46
     exasper
    0.45
    iy
    0.45
    ція
    0.45
    ドア
    0.44
    transformers
    0.44
    ല്ലാ
    0.44
     Projek
    0.44
    pees
    0.42
    Activations Density 0.000%

    No Known Activations