© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48593
    Prev
    Next
    INDEX
    Explanations

    property name=".*"

    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
    钨
    -0.80
    Extent
    -0.78
    Packet
    -0.77
     eszköz
    -0.76
     roulant
    -0.75
     žena
    -0.75
    rte
    -0.75
    rna
    -0.75
     fontos
    -0.74
     connected
    -0.74
    POSITIVE LOGITS
     name
    1.72
    name
    1.10
     names
    1.02
     namens
    0.96
     Name
    0.93
     ref
    0.89
    REF
    0.86
    Name
    0.84
    ref
    0.83
     namely
    0.80
    Activations Density 0.008%

    No Known Activations