© 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. 93165
    Prev
    Next
    INDEX
    Explanations

    URLs and citations

    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
    itemBuilder
    -0.88
    ==-
    -0.81
     Fir
    -0.80
     também
    -0.79
    ĝis
    -0.78
     BOTH
    -0.77
     lorem
    -0.77
     ALS
    -0.75
     Chal
    -0.75
     Bat
    -0.75
    POSITIVE LOGITS
     Retrieved
    2.25
    Retrieved
    1.39
     retrieved
    1.36
     doi
    1.26
     https
    1.20
     http
    1.17
    https
    1.09
    http
    1.02
     Recuperado
    1.00
     other
    0.96
    Activations Density 0.001%

    No Known Activations