© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113773
    Prev
    Next
    INDEX
    Explanations

    Knox Cameron, Ricardo footballer, MSC

    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
     técn
    -2.39
    días
    -2.20
    istán
    -2.17
    滏
    -2.08
     egip
    -2.08
    𖡼
    -2.06
    sigue
    -2.05
     for
    -2.03
    Ꮙ
    -1.97
     Diciembre
    -1.96
    POSITIVE LOGITS
    l
    2.78
    al
    2.66
    in
    2.53
    d
    2.42
    en
    2.33
    </h1>
    2.30
     –
    2.30
    2.20
     So
    2.11
            
    2.06
    Activations Density 0.001%

    No Known Activations