© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40486
    Prev
    Next
    INDEX
    Explanations

    earthquake

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    9
    -4.06
    .”
    -3.33
    You
    -3.16
    ’
    -3.08
    This
    -3.06
    ".
    -2.98
    7
    -2.97
    of
    -2.94
    ?"
    -2.91
    2
    -2.83
    POSITIVE LOGITS
    ↵↵
    2.67
    **
    2.64
    鈇
    2.59
    鷸
    2.58
    だろ
    2.56
    髡
    2.50
    骝
    2.45
     parachoque
    2.42
     gebouw
    2.39
    埭
    2.39
    Activations Density 0.002%

    No Known Activations