© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 117398
    Prev
    Next
    INDEX
    Explanations

    you should

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

    catalytic dehydrogenation, tall fins, vascular territories, carbon credits

    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
     méthodes
    0.46
    חק
    0.46
     versionName
    0.45
    δώ
    0.45
    <unused96>
    0.45
     ਦਵਾਈ
    0.44
     smoked
    0.44
     starred
    0.44
     पीड़
    0.44
    ложении
    0.43
    POSITIVE LOGITS
    n
    0.62
    트
    0.50
     Regional
    0.49
    en
    0.48
     అంటే
    0.48
    L
    0.46
    ile
    0.46
     Фила
    0.46
    마
    0.46
    l
    0.46
    Activations Density 0.000%

    No Known Activations