© 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. 60916
    Prev
    Next
    INDEX
    Explanations

    street and number

    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
     mengenai
    -0.79
    motif
    -0.79
    唄
    -0.75
    平均
    -0.74
    colormap
    -0.74
    anguages
    -0.71
    </tfoot>
    -0.71
    checkpoint
    -0.70
    ogyn
    -0.69
     кор
    -0.67
    POSITIVE LOGITS
     street
    3.52
    street
    2.69
     Street
    2.64
     streets
    2.63
    Street
    2.50
    STREET
    2.34
     STREET
    2.30
     address
    1.95
     house
    1.93
     Streets
    1.89
    Activations Density 0.020%

    No Known Activations