© 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. 61388
    Prev
    Next
    INDEX
    Explanations

    demonstration

    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
    遢
    -2.27
    ra
    -2.27
     bliss
    -2.20
    是
    -2.17
    after
    -2.13
     AFTER
    -2.08
    在此
    -2.08
     как
    -2.08
     tuvo
    -2.06
     vostre
    -2.06
    POSITIVE LOGITS
    </h3>
    2.77
    ”.
    2.38
    
    2.34
    泚
    2.30
     sebagainya
    2.30
     ()
    2.27
    .
    2.23
     """
    2.22
    哢
    2.16
    这件事
    2.13
    Activations Density 0.006%

    No Known Activations