© 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. 100364
    Prev
    Next
    INDEX
    Explanations

    recognition of specific roles or groups

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

    list of items

    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
    貶
    0.54
     dail
    0.47
     Shakespeare
    0.47
     Nasdaq
    0.46
     Scand
    0.46
     Bank
    0.46
     composição
    0.45
    ὡ
    0.45
     fax
    0.44
    িউ
    0.44
    POSITIVE LOGITS
    ول
    0.59
     कैंडिडेट्स
    0.53
     می‌
    0.51
    Figs
    0.49
    Candidates
    0.49
     جایی
    0.48
    Alles
    0.48
     واحد
    0.47
    Après
    0.47
    aft
    0.46
    Activations Density 0.001%

    No Known Activations