© 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. 72465
    Prev
    Next
    INDEX
    Explanations

    state or condition descriptors

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

    literal translation options

    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
    disconnected
    0.52
    лок
    0.50
    ünüz
    0.49
    ルダー
    0.48
    ünün
    0.47
     जनगणना
    0.45
    ؤس
    0.45
    ﺔ
    0.44
    லம்
    0.44
    㞖
    0.43
    POSITIVE LOGITS
     uska
    0.46
     tbh
    0.46
     barang
    0.45
     bairro
    0.45
     wx
    0.44
    }_
    0.43
     pq
    0.43
     barrio
    0.43
     inland
    0.43
     pump
    0.42
    Activations Density 0.001%

    No Known Activations