© 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. 234455
    Prev
    Next
    INDEX
    Explanations

    Select, mandatory, owner

    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
    ΐ
    0.50
    ܗ
    0.46
    礽
    0.42
    یز
    0.42
    ум
    0.41
    اوی
    0.40
    約
    0.40
    ностью
    0.40
    ρχ
    0.39
     abgeschlossen
    0.39
    POSITIVE LOGITS
     براي
    0.56
     ડ
    0.51
     terá
    0.51
     국
    0.50
    ellten
    0.50
     ફો
    0.48
     নয়ন
    0.48
     Ó
    0.46
     ダイ
    0.46
     مكان
    0.46
    Activations Density 0.001%

    No Known Activations