© 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. 183785
    Prev
    Next
    INDEX
    Explanations

    ISBN or discount

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

    animal studies

    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
    各种
    0.48
    PreferenceKeys
    0.47
    现有
    0.47
     экране
    0.45
     स्क्रीन
    0.45
    
    0.45
    你应该
    0.44
    可能会
    0.44
    钥匙
    0.44
    卫
    0.44
    POSITIVE LOGITS
     izra
    0.50
    Tanggal
    0.48
    mey
    0.47
    oky
    0.46
     colo
    0.43
     Berlusconi
    0.43
    atot
    0.43
    igay
    0.43
    it
    0.43
    emel
    0.43
    Activations Density 0.001%

    No Known Activations