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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103116
    Prev
    Next
    INDEX
    Explanations

    greater than or equal to number

    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
    
    -2.66
    ܜ
    -2.63
                    
    -2.53
    -2.42
    ・・・」
    -2.42
     實
    -2.38
    豨
    -2.36
    -2.34
    っす
    -2.25
    This
    -2.19
    POSITIVE LOGITS
     we
    3.11
    毉
    2.58
    ↵
    2.33
     goede
    2.31
     .
    2.30
    淡淡
    2.28
     mayoría
    2.22
    '
    2.17
     wuß
    2.13
    quele
    2.11
    Activations Density 0.005%

    No Known Activations