© 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. 198206
    Prev
    Next
    INDEX
    Explanations

    initial, bay, vacuum, baking, gay, crack

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

    reading sentences

    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
     McDonnell
    0.49
     Simultaneous
    0.49
     RELEASE
    0.48
     LOCK
    0.47
     Mechanical
    0.47
     Performance
    0.46
     Topological
    0.45
    诊
    0.45
     Garage
    0.45
     CD
    0.45
    POSITIVE LOGITS
    breeds
    0.54
    غ
    0.53
    packing
    0.52
    estimates
    0.50
     acab
    0.49
    emplo
    0.48
    conoc
    0.48
     أمر
    0.47
    strukt
    0.47
     breeds
    0.47
    Activations Density 0.000%

    No Known Activations