© 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. 38686
    Prev
    Next
    INDEX
    Explanations

    first round second round

    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
     semifinal
    -1.07
    SEM
    -0.97
     quarter
    -0.93
     सेमी
    -0.91
     semi
    -0.86
     semifinals
    -0.84
     SEMI
    -0.81
     graag
    -0.78
     hablan
    -0.78
    semi
    -0.77
    POSITIVE LOGITS
     sophomore
    0.79
    anderen
    0.74
     Third
    0.74
     opening
    0.73
    opia
    0.72
    Conditional
    0.71
     Central
    0.70
     Cause
    0.70
    ામ
    0.69
     Second
    0.69
    Activations Density 0.030%

    No Known Activations