© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59167
    Prev
    Next
    INDEX
    Explanations

    names: Toni, Carmen, Merritt

    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
    *
    -3.38
    0
    -3.28
    ?
    -2.97
    “
    -2.94
    &
    -2.83
    '
    -2.67
    祘
    -2.58
    1
    -2.52
        
    -2.48
    6
    -2.44
    POSITIVE LOGITS
    逦
    3.27
    鲼
    3.02
    」、「
    2.50
    醱
    2.47
    卣
    2.45
    瓛
    2.42
    盌
    2.39
     utiliser
    2.39
    ᗢ
    2.34
    इटम
    2.27
    Activations Density 0.002%

    No Known Activations