© 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. 130914
    Prev
    Next
    INDEX
    Explanations

    free WiFi or parking

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

    Fort Weekend Building

    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
    ный
    0.53
    לי
    0.52
    у
    0.51
    gart
    0.50
    户
    0.49
    璟
    0.48
    поряд
    0.48
    пи
    0.47
    ى
    0.47
    же
    0.46
    POSITIVE LOGITS
     incredibly
    0.49
     خودش
    0.47
     मैच
    0.46
     buckles
    0.46
     welds
    0.45
     egot
    0.45
     tamper
    0.44
     Tuck
    0.43
     retention
    0.43
     tuck
    0.43
    Activations Density 0.001%

    No Known Activations