© 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. 102615
    Prev
    Next
    INDEX
    Explanations

    go away

    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
     درآمد
    -0.81
    ppa
    -0.77
    Público
    -0.75
    Reuse
    -0.74
    原谅
    -0.74
    маны
    -0.72
    зани
    -0.72
    izan
    -0.71
    ște
    -0.71
     ghetto
    -0.71
    POSITIVE LOGITS
     go
    2.19
     leave
    1.59
     stay
    1.55
     get
    1.54
    滚
    1.52
     Leave
    1.40
    Leave
    1.38
    leave
    1.34
     Go
    1.32
    Go
    1.32
    Activations Density 0.036%

    No Known Activations