© 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. 34-GEMMASCOPE-RES-131K
    7. 93284
    Prev
    Next
    INDEX
    Explanations

    configuration and code delimiters

    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_34/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
    čios
    -0.96
     européennes
    -0.94
    Nun
    -0.91
    ýchod
    -0.88
    
    -0.88
     duod
    -0.87
     Staphylococcus
    -0.86
     Salto
    -0.85
    Dann
    -0.85
    ଷ
    -0.85
    POSITIVE LOGITS
     here
    1.28
     and
    1.23
     queste
    1.19
     Here
    1.18
     These
    1.16
     crescita
    1.08
     Such
    1.06
     ();
    1.05
    ody
    1.02
     these
    1.01
    Activations Density 0.002%

    No Known Activations