© 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. 234272
    Prev
    Next
    INDEX
    Explanations

    deductions and financial details

    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
    رى
    0.49
     toutefois
    0.48
    cY
    0.48
     Gebiet
    0.47
    zné
    0.46
     geleden
    0.46
    zq
    0.46
    ધ
    0.46
     STADT
    0.46
     पिस्टल
    0.46
    POSITIVE LOGITS
    の内容
    0.45
     skapa
    0.44
     descripcion
    0.43
    議題
    0.43
    主题
    0.42
     Gaia
    0.42
     idea
    0.41
    問題
    0.38
     ড
    0.38
     announcer
    0.38
    Activations Density 0.002%

    No Known Activations