© 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. 161858
    Prev
    Next
    INDEX
    Explanations

    specific subjects

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

    legal and casual contexts

    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
    頓
    0.49
    最後
    0.48
     defensive
    0.48
    後
    0.47
    完成
    0.46
    綜
    0.46
    كس
    0.46
    ασ
    0.46
    新
    0.45
    顿
    0.44
    POSITIVE LOGITS
     ไหร่
    0.52
    ulfanyl
    0.50
     набу
    0.50
     स्वतः
    0.49
     пси
    0.47
     ગાં
    0.46
    obbly
    0.44
    ində
    0.43
     භ
    0.43
    imetro
    0.43
    Activations Density 0.000%

    No Known Activations