© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30679
    Prev
    Next
    INDEX
    Explanations

    Concordia University Irvine Seminary

    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
    )!
    -0.78
    FOCUS
    -0.76
     bien
    -0.75
    焦点
    -0.74
     masing
    -0.73
     retira
    -0.71
     !!!
    -0.71
     hacía
    -0.69
     mengg
    -0.68
    ))
    -0.68
    POSITIVE LOGITS
    Loy
    1.09
     Loyola
    0.79
    Soorten
    0.78
     subgoal
    0.75
    深圳
    0.74
     Skeletal
    0.74
     incr
    0.73
    LOY
    0.73
     saluti
    0.73
    シカ
    0.72
    Activations Density 0.005%

    No Known Activations