© 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. 59472
    Prev
    Next
    INDEX
    Explanations

    code identifiers and structure

    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
    henswürdigkeiten
    -1.55
    最重要的
    -1.47
     других
    -1.44
     产品
    -1.41
     інші
    -1.41
     dicono
    -1.38
     userDetails
    -1.38
    ”—
    -1.38
    brando
    -1.37
     definitively
    -1.35
    POSITIVE LOGITS
     nummer
    1.33
    และ
    1.31
    龉
    1.27
     chaussures
    1.26
    pike
    1.23
    CCIÓN
    1.22
    沨
    1.22
    ancing
    1.20
     preparar
    1.18
    employed
    1.18
    Activations Density 0.008%

    No Known Activations