© 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. 83891
    Prev
    Next
    INDEX
    Explanations

    enum type declarations

    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
    <eos>
    -0.88
     curiously
    -0.83
     înainte
    -0.82
     admittedly
    -0.78
     interestingly
    -0.75
     costas
    -0.74
    olites
    -0.74
    Ainda
    -0.74
     convincingly
    -0.73
    ♂
    -0.73
    POSITIVE LOGITS
    </h2>
    3.88
    </h3>
    3.36
    </h1>
    3.30
    </h4>
    3.28
    </h5>
    3.00
    </h6>
    2.55
    </blockquote>
    2.00
    </strong>
    1.91
    </b>
    1.88
    </th>
    1.82
    Activations Density 0.061%

    No Known Activations