© 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. 59461
    Prev
    Next
    INDEX
    Explanations

    cloud. Office 365

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

    categorized and explained

    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
     reflexive
    0.48
     praktische
    0.45
     diamant
    0.44
    ッセージ
    0.44
     berg
    0.43
    ened
    0.43
     gummy
    0.41
    ꒷
    0.41
     vier
    0.41
     chord
    0.41
    POSITIVE LOGITS
     ıs
    0.52
    Proveedor
    0.49
     للن
    0.49
     Administration
    0.48
     पराम
    0.46
     Австра
    0.46
    ىسى
    0.46
    Interpretation
    0.44
     அறு
    0.44
    BUG
    0.44
    Activations Density 0.000%

    No Known Activations