© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66385
    Prev
    Next
    INDEX
    Explanations

    positive appraisals of services and items

    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
     to
    -1.93
     or
    -1.72
     for
    -1.33
     into
    -1.20
     julho
    -1.13
     volledige
    -1.06
     möglichst
    -1.06
    zah
    -1.03
    apter
    -1.02
    の部分
    -1.02
    POSITIVE LOGITS
     sekä
    1.28
     both
    1.27
    acité
    1.21
    也很
    1.18
     people
    1.15
     PÅ
    1.10
     JMenuItem
    1.10
    óval
    1.08
     ProductService
    1.07
     services
    1.05
    Activations Density 0.010%

    No Known Activations