© 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. 72025
    Prev
    Next
    INDEX
    Explanations

    performance or trade

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

    Transformer licensing

    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
     פר
    0.52
    ție
    0.49
    چ
    0.48
    崙
    0.46
     gepub
    0.46
    ציה
    0.45
    经
    0.44
     медици
    0.44
    ﭼ
    0.43
    的内容
    0.42
    POSITIVE LOGITS
    いっぱい
    0.49
     andDevice
    0.46
    釦
    0.46
     वर्ग
    0.45
    ibley
    0.45
     _)
    0.44
    emark
    0.44
     linings
    0.43
    線性
    0.43
    eniem
    0.43
    Activations Density 0.000%

    No Known Activations