© 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. 59140
    Prev
    Next
    INDEX
    Explanations

    focused on research directions

    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
     masih
    -1.55
    erapeutics
    -1.44
    zione
    -1.44
     coreana
    -1.44
     løpet
    -1.35
    inerario
    -1.35
     vegano
    -1.31
    によっては
    -1.30
     udang
    -1.30
    据说
    -1.27
    POSITIVE LOGITS
     to
    1.55
    它
    1.50
     úrov
    1.41
     extraña
    1.37
     レア
    1.31
    яг
    1.30
    actualité
    1.28
     входят
    1.27
     vorigen
    1.27
    เพื่อ
    1.26
    Activations Density 0.069%

    No Known Activations