© 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. 96654
    Prev
    Next
    INDEX
    Explanations

    parts of words and numbers

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

    UI / Interface

    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
    a
    0.42
    癇
    0.42
    いち
    0.41
     коллекции
    0.40
    學者
    0.40
     त्यो
    0.39
    აზე
    0.39
    器
    0.39
    Methods
    0.39
    Putin
    0.38
    POSITIVE LOGITS
     accion
    0.46
     helfen
    0.46
     macht
    0.46
    utsch
    0.45
     femenina
    0.45
     مشرقی
    0.45
     corrige
    0.44
    üşt
    0.44
     actualizada
    0.43
     لیکن
    0.43
    Activations Density 0.000%

    No Known Activations