© 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. 48428
    Prev
    Next
    INDEX
    Explanations

    thank you

    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
    ),
    -2.63
     來
    -2.17
            
    -2.16
     use
    -2.11
     ciepła
    -2.09
    with
    -1.96
     If
    -1.88
     It
    -1.87
    ge
    -1.85
    H
    -1.84
    POSITIVE LOGITS
     炖
    2.19
    鷽
    2.16
    鮡
    2.13
    蠵
    2.06
     incrí
    2.00
    髕
    2.00
    踯
    1.95
    烔
    1.93
     dê
    1.92
     statut
    1.91
    Activations Density 0.005%

    No Known Activations