© 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. 31837
    Prev
    Next
    INDEX
    Explanations

    software license notice

    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
     Worldwide
    -0.71
    ˃
    -0.70
     Salter
    -0.68
     compliance
    -0.66
    瑜
    -0.66
     őket
    -0.65
     Statutory
    -0.65
    Ralph
    -0.61
     mendorong
    -0.61
     dryness
    -0.60
    POSITIVE LOGITS
     Birken
    0.74
     Instability
    0.72
    usec
    0.69
    letti
    0.68
    ванта
    0.66
    색
    0.66
    masters
    0.65
     Stabilization
    0.65
     playlists
    0.65
    APL
    0.64
    Activations Density 0.071%

    No Known Activations