© 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. 16150
    Prev
    Next
    INDEX
    Explanations

    technical language, code, and math

    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
    다
    0.50
    ang
    0.46
    urde
    0.46
    ech
    0.46
    research
    0.45
     penelitian
    0.44
    nc
    0.43
    ue
    0.43
    ‘‘
    0.43
     research
    0.42
    POSITIVE LOGITS
    toFloat
    0.47
     gaskets
    0.46
    قامة
    0.44
    虢
    0.43
    فهام
    0.41
    兑
    0.41
    ፈላጊ
    0.40
    ๛
    0.40
    冚
    0.39
    شكال
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.