© 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. 220089
    Prev
    Next
    INDEX
    Explanations

    first hurdle

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

    innovation, spreadsheets, pipeline

    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
    zeug
    0.44
    语言
    0.44
    teller
    0.43
    诬
    0.43
    经常
    0.42
    经
    0.42
    称为
    0.41
    Obs
    0.41
     Museum
    0.41
    俨
    0.41
    POSITIVE LOGITS
     okra
    0.49
     sowing
    0.48
     trapping
    0.48
     shearing
    0.48
     tassels
    0.47
     AVAILABLE
    0.47
     CAPACITY
    0.47
     AID
    0.47
    ABET
    0.46
     overcrow
    0.46
    Activations Density 0.006%

    No Known Activations