© 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. 12230
    Prev
    Next
    INDEX
    Explanations

    the word marks

    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
    \
    -3.47
    ].
    -2.94
    <i>
    -2.53
     onze
    -2.48
    B
    -2.45
     dieses
    -2.41
    U
    -2.36
     ezt
    -2.31
    ve
    -2.25
     ؟
    -2.25
    POSITIVE LOGITS
     possono
    2.61
    
    2.44
     incluem
    2.42
     sogen
    2.41
     bemerkt
    2.38
    er
    2.38
     gelernt
    2.38
     săptăm
    2.38
    一旦
    2.36
    錼
    2.36
    Activations Density 0.004%

    No Known Activations