© 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. 133824
    Prev
    Next
    INDEX
    Explanations

    risk and reward

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

    remote computer, translation, prizes

    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
     quinquina
    0.54
    escape
    0.46
    tracking
    0.46
    key
    0.45
    ផុត
    0.45
    reverse
    0.44
    ileg
    0.44
    {|\
    0.44
    destroyed
    0.43
    })}
    0.43
    POSITIVE LOGITS
     aé
    0.52
    鮒
    0.50
     ciudadano
    0.49
     বিজ্ঞাপন
    0.48
     Cram
    0.48
    コレート
    0.47
    馇
    0.46
    ﻊ
    0.46
     Vicar
    0.46
     Amateur
    0.46
    Activations Density 0.000%

    No Known Activations