© 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. 116629
    Prev
    Next
    INDEX
    Explanations

    official permissions and approvals

    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
    Scul
    -0.74
    Loyalty
    -0.73
    arro
    -0.68
     scul
    -0.67
    orgt
    -0.65
     Scul
    -0.65
    laß
    -0.65
    amientos
    -0.65
    绺
    -0.64
     frecuentes
    -0.64
    POSITIVE LOGITS
     permit
    1.98
     inspections
    1.75
     permits
    1.74
     Permit
    1.73
     inspection
    1.66
    Permit
    1.56
     building
    1.54
     Building
    1.53
    permit
    1.50
     inspectors
    1.47
    Activations Density 0.011%

    No Known Activations