© 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. 10-GEMMASCOPE-RES-131K
    4. 12386
    Prev
    Next
    INDEX
    Explanations

    athletics, photographic, following text

    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_10/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
    ?
    -3.02
    \
    -2.95
    AutoresizingMask
    -2.70
    <i>
    -2.56
    </td>
    -2.56
    *
    -2.42
    2
    -2.39
    ).
    -2.33
    ли
    -2.33
    </b>
    -2.27
    POSITIVE LOGITS
    ?”
    3.28
     Zeitraum
    2.84
    俅
    2.67
    女朋友
    2.55
     anguish
    2.52
     gustaba
    2.52
     pareció
    2.50
    }$
    2.45
     numerosas
    2.44
     tocó
    2.42
    Activations Density 0.011%

    No Known Activations