© 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. 103835
    Prev
    Next
    INDEX
    Explanations

    Calgary and Abdul names

    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
    2
    -3.72
    '
    -3.14
    4
    -3.11
    9
    -3.08
    3
    -3.06
    ↵
    -3.03
    <em>
    -2.97
    6
    -2.89
    S
    -2.73
    1
    -2.70
    POSITIVE LOGITS
    嘬
    2.75
    絰
    2.63
    ”？
    2.58
    釭
    2.56
    ⤴
    2.53
    
    2.53
    蹰
    2.48
    評判
    2.48
     bluza
    2.42
     декабря
    2.41
    Activations Density 0.002%

    No Known Activations