© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99300
    Prev
    Next
    INDEX
    Explanations

    adjective noun phrases

    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
     STREET
    -1.04
     DANCE
    -0.99
     CENTER
    -0.97
     simpel
    -0.95
     dégâts
    -0.93
    ouſ
    -0.93
    lesse
    -0.91
     CROSS
    -0.91
     PARK
    -0.91
     DRIVE
    -0.91
    POSITIVE LOGITS
     Такие
    0.96
     these
    0.91
     Joe
    0.85
     Многие
    0.85
     any
    0.84
     for
    0.83
     as
    0.80
     some
    0.79
     when
    0.77
    lifier
    0.77
    Activations Density 0.085%

    No Known Activations