© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70848
    Prev
    Next
    INDEX
    Explanations

    stunt or stunted

    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
    谖
    -2.59
    戩
    -2.42
    ل
    -2.23
    鲀
    -2.23
    0
    -2.09
    uttgart
    -2.03
     gracefully
    -2.02
    ܃
    -2.00
     撮り
    -1.98
    ㌘
    -1.96
    POSITIVE LOGITS
    gefügt
    2.45
    ],
    2.45
    澌
    2.42
    ,"
    2.33
    ’
    2.27
    these
    2.27
    埽
    2.22
    ־
    2.20
    ',
    2.14
    .$,
    2.13
    Activations Density 0.002%

    No Known Activations