© 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. 68347
    Prev
    Next
    INDEX
    Explanations

    email sign-off names

    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
     If
    -1.81
     there
    -1.59
    Britannique
    -1.56
     that
    -1.55
     alábbi
    -1.55
    вим
    -1.50
     it
    -1.46
     to
    -1.46
     You
    -1.42
     sorprendente
    -1.41
    POSITIVE LOGITS
    她的
    1.52
    谎
    1.50
     gewi
    1.42
    缤
    1.41
    变了
    1.40
    どもの
    1.40
     измени
    1.38
     ecran
    1.36
    都是
    1.35
    0
    1.35
    Activations Density 0.022%

    No Known Activations