© 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. 25857
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    Continue
    -0.90
    īm
    -0.89
    venidos
    -0.84
    ستاگرام
    -0.82
     "{}
    -0.81
     circulated
    -0.81
    getDescription
    -0.80
    ……………………
    -0.78
     esimer
    -0.77
    źć
    -0.77
    POSITIVE LOGITS
     reply
    1.30
     Forum
    1.04
     replies
    1.04
     forums
    1.02
     response
    1.02
     forum
    1.02
     replying
    0.99
     napisa
    0.98
     moderator
    0.97
    reply
    0.96
    Activations Density 0.086%

    No Known Activations