© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107292
    Prev
    Next
    INDEX
    Explanations

    outcome of

    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
    菈
    -1.05
    ctron
    -0.97
    ghijklmnop
    -0.95
    ⟳
    -0.94
    🗿
    -0.94
    tvrt
    -0.93
    遑
    -0.93
     aarde
    -0.93
     estekak
    -0.93
    vejec
    -0.92
    POSITIVE LOGITS
     them
    3.56
     him
    2.83
     us
    2.39
     having
    2.36
     someone
    2.17
     people
    1.92
     there
    1.88
     somebody
    1.87
     seeing
    1.82
     being
    1.80
    Activations Density 0.110%

    No Known Activations