© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103517
    Prev
    Next
    INDEX
    Explanations

    file paths and code comments

    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
     estes
    -0.93
     FUCKING
    -0.84
     craftsmen
    -0.83
     Pdf
    -0.83
     sequestration
    -0.82
     DREAM
    -0.82
     TRUST
    -0.81
     PLAY
    -0.79
    Sic
    -0.78
     Cbd
    -0.78
    POSITIVE LOGITS
     want
    0.91
     Meksiku
    0.89
    ByID
    0.87
     options
    0.86
     must
    0.84
    hasMany
    0.83
     acondicionado
    0.82
     wants
    0.82
     require
    0.81
     府
    0.80
    Activations Density 0.084%

    No Known Activations