© 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. 163258
    Prev
    Next
    INDEX
    Explanations

    friendly service

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

    models and settings

    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
    n
    0.57
    DATA
    0.50
    -
    0.50
    ai
    0.48
    AI
    0.46
    e
    0.46
    AR
    0.45
    rr
    0.45
    x
    0.45
    දා
    0.45
    POSITIVE LOGITS
     sätt
    0.59
     virtuel
    0.53
     ड्रीम
    0.50
     टाइप्स
    0.50
     ऑनर्स
    0.48
     headsets
    0.47
     consoles
    0.47
     économiques
    0.47
     invités
    0.46
     স্বপ্নের
    0.46
    Activations Density 0.000%

    No Known Activations