© 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. 136550
    Prev
    Next
    INDEX
    Explanations

    comma before Permalink or Tags

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

    legal terms followed by context

    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
     Kristian
    0.46
    这是一个
    0.43
    你是
    0.42
     erwähnt
    0.42
     Crist
    0.41
     krist
    0.41
    概率
    0.41
    <0x9C>
    0.40
    摈
    0.40
    akrishna
    0.40
    POSITIVE LOGITS
    các
    0.57
    ל
    0.57
    اویر
    0.55
    ل
    0.52
    කර
    0.50
     ச
    0.50
    вич
    0.49
    л
    0.48
    ג
    0.47
     hubungan
    0.47
    Activations Density 0.000%

    No Known Activations