© 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. 1374
    Prev
    Next
    INDEX
    Explanations

    sessions and classes

    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
     counseling
    -0.89
     путем
    -0.87
     Counseling
    -0.87
     deficient
    -0.85
     honored
    -0.85
     physicians
    -0.84
     neighbors
    -0.82
     normalized
    -0.82
     Cape
    -0.81
     neighborhood
    -0.79
    POSITIVE LOGITS
     sessions
    1.85
     session
    1.52
    sessions
    1.40
    session
    1.27
    Sessions
    1.23
     booking
    1.17
    getSession
    1.13
     Sessions
    1.13
    SESSION
    1.09
    Session
    1.05
    Activations Density 0.027%

    No Known Activations