© 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. 58639
    Prev
    Next
    INDEX
    Explanations

    not followed by a verb

    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
     to
    -2.55
     of
    -2.55
    .”
    -2.52
     täglichen
    -2.38
     vollständ
    -2.28
     biggest
    -2.27
     äußerst
    -2.17
     schnellen
    -2.13
     then
    -2.09
     --
    -2.08
    POSITIVE LOGITS
     verhind
    2.58
    缯
    2.50
    踭
    2.30
    埽
    2.25
    甃
    2.23
    琑
    2.17
     ſta
    2.16
     VARCHAR
    2.14
    噐
    2.13
     ENGLISH
    2.11
    Activations Density 0.019%

    No Known Activations