© 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. 6960
    Prev
    Next
    INDEX
    Explanations

    SNAPSHOT</version>

    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
     “
    -1.05
     powinny
    -0.91
    louis
    -0.91
     “[
    -0.90
    helen
    -0.90
    laquo
    -0.90
     that
    -0.86
    民國
    -0.86
    lisi
    -0.85
    assero
    -0.84
    POSITIVE LOGITS
    </
    1.27
    これも
    1.07
    こちらも
    1.03
    '],
    1.02
    siert
    1.02
    </i>
    1.00
    '),
    1.00
    "/>
    0.95
    </tr>
    0.94
    "),
    0.93
    Activations Density 0.004%

    No Known Activations