© 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. 33853
    Prev
    Next
    INDEX
    Explanations

    technical components and applications

    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
     and
    -1.27
     it
    -1.22
     one
    -1.13
     people
    -1.09
     continual
    -1.05
     an
    -1.05
     believes
    -1.04
     additional
    -1.00
     Creating
    -0.99
     or
    -0.97
    POSITIVE LOGITS
    depuis
    1.23
    を中心に
    1.22
     และ
    1.22
    primarily
    1.20
    generally
    1.16
    particularly
    1.10
     การ
    1.09
    mainly
    1.09
     BLUE
    1.09
     แท
    1.09
    Activations Density 0.184%

    No Known Activations