© 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. 25337
    Prev
    Next
    INDEX
    Explanations

    numbers and reports

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

    indicative of potential issues

    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
    Answer
    0.53
    Section
    0.53
    A
    0.52
    ProjectId
    0.51
    ญิง
    0.48
    Bam
    0.48
    Pose
    0.48
    Assume
    0.48
    Project
    0.47
    Address
    0.47
    POSITIVE LOGITS
     文件
    0.54
     Sedangkan
    0.50
     工作
    0.47
     不是
    0.47
     Metals
    0.45
    鏤
    0.45
     其他
    0.44
     食品
    0.44
    iros
    0.44
    ibers
    0.44
    Activations Density 0.000%

    No Known Activations