© 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. 34-GEMMASCOPE-RES-131K
    7. 49809
    Prev
    Next
    INDEX
    Explanations

    potential benefit or solution

    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_34/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
     tempel
    -1.12
     kolam
    -1.08
     ryt
    -1.07
    +
    -1.06
    　　《
    -1.04
     hvil
    -1.03
    neurs
    -1.01
     meren
    -1.01
    skechers
    -1.00
     persen
    -0.98
    POSITIVE LOGITS
     help
    2.88
     be
    1.79
     benefits
    1.56
     revolution
    1.53
    help
    1.52
     provide
    1.52
    ช่วย
    1.52
     benefit
    1.50
     aid
    1.44
     contribute
    1.44
    Activations Density 0.060%

    No Known Activations