© 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. 135187
    Prev
    Next
    INDEX
    Explanations

    institutional problem never area station active detective

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

    increasingly important

    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
    QTTR
    0.57
     returning
    0.53
    entionally
    0.50
    koľ
    0.49
     bookArray
    0.48
     InputStream
    0.47
     옮
    0.47
    नोई
    0.47
     कस्
    0.47
     Returning
    0.47
    POSITIVE LOGITS
    p
    0.56
    x
    0.52
     keinen
    0.48
    word
    0.48
    plus
    0.47
    eine
    0.47
    قيقي
    0.46
     рост
    0.45
    واقع
    0.45
    ريم
    0.44
    Activations Density 0.001%

    No Known Activations