© 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. 22-GEMMASCOPE-RES-131K
    7. 34140
    Prev
    Next
    INDEX
    Explanations

    then

    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_22/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
     ilyen
    -1.10
     additional
    -1.02
     JULIO
    -1.02
    ৄ
    -1.00
     PEDRO
    -1.00
    Einzelnachweise
    -0.97
    these
    -0.96
     high
    -0.96
     świecie
    -0.96
    いただきたい
    -0.94
    POSITIVE LOGITS
    では
    1.25
    <bos>
    1.02
     затем
    1.02
     then
    1.00
    имущества
    0.97
    aney
    0.92
     سپس
    0.91
     Cras
    0.91
    ñ
    0.90
    охра
    0.89
    Activations Density 0.014%

    No Known Activations