© 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. 221883
    Prev
    Next
    INDEX
    Explanations

    legal, financial, and technical terms

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

    taking a spot

    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
    Bo
    0.49
    示す
    0.49
    偏
    0.47
    ່ຽ
    0.46
     کنند
    0.46
    仔
    0.45
     therefor
    0.44
    MG
    0.44
    parsedBlock
    0.43
    Ë
    0.43
    POSITIVE LOGITS
     사건
    0.52
     býval
    0.46
    儩
    0.46
     괴
    0.45
     공격
    0.45
     reconnaissance
    0.45
    үз
    0.44
     cur
    0.43
     događ
    0.43
     kraj
    0.43
    Activations Density 0.001%

    No Known Activations