© 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. 223492
    Prev
    Next
    INDEX
    Explanations

    President Trump

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

    earliest political; wheels wear

    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
     ஆண
    0.50
    ıp
    0.47
     appBar
    0.47
     అనేక
    0.47
    ету
    0.46
    ی
    0.46
     andRow
    0.44
     inhom
    0.44
     vũ
    0.44
     растений
    0.44
    POSITIVE LOGITS
    to
    0.48
    音声
    0.45
    思
    0.43
    無
    0.43
    time
    0.42
    }
    0.41
    buffer
    0.41
    凄
    0.41
    territ
    0.41
    bae
    0.40
    Activations Density 0.002%

    No Known Activations