© 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. 92244
    Prev
    Next
    INDEX
    Explanations

    in or at locations

    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
     always
    -0.83
    ーん
    -0.77
    tekend
    -0.73
    的意思
    -0.73
     siempre
    -0.73
    ökk
    -0.72
     چنین
    -0.71
     Jahrgang
    -0.71
    PONSE
    -0.71
    のも
    -0.71
    POSITIVE LOGITS
     places
    3.78
     места
    3.20
    places
    2.98
    Places
    2.95
     parts
    2.80
     Places
    2.77
     spots
    2.72
     PLACES
    2.41
     міс
    2.30
     lugares
    2.16
    Activations Density 0.031%

    No Known Activations