© 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. 22-GEMMASCOPE-RES-131K
    7. 54139
    Prev
    Next
    INDEX
    Explanations

    sculptures and sculptors

    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_22/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
    -2.39
    9
    -2.33
    6
    -2.20
    8
    -2.17
    7
    -2.00
    This
    -1.95
    s
    -1.88
    熥
    -1.80
     =
    -1.79
     giù
    -1.77
    POSITIVE LOGITS
    ↵
    3.05
    <bos>
    2.28
    ,’
    2.13
     bené
    2.02
     feitos
    1.98
    ’，
    1.98
     “
    1.95
    ?”
    1.92
    ጵ
    1.90
     of
    1.89
    Activations Density 0.017%

    No Known Activations