© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63536
    Prev
    Next
    INDEX
    Explanations

    conference sessions

    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
    guest
    -0.84
     Monthly
    -0.82
     monthly
    -0.74
    Monthly
    -0.73
    Weekly
    -0.71
     extravagant
    -0.71
    umers
    -0.71
    student
    -0.70
    交往
    -0.68
     måned
    -0.68
    POSITIVE LOGITS
     session
    2.95
     sessions
    2.84
    session
    2.34
    Session
    2.33
     Session
    2.22
    Sessions
    2.03
     Sessions
    2.03
    sessions
    1.98
    SESSION
    1.91
     SESSION
    1.87
    Activations Density 0.031%

    No Known Activations