© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 33360
    Prev
    Next
    INDEX
    Explanations

    scientific and programming contexts

    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_22/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
     which
    -1.18
     including
    -1.03
     that
    -0.92
     Except
    -0.91
     this
    -0.91
     After
    -0.90
    itmen
    -0.90
    できるので
    -0.88
    <i>
    -0.87
    ḷ
    -0.87
    POSITIVE LOGITS
    </strong>
    2.50
    </em>
    2.34
    </i>
    2.14
    </b>
    1.84
    </code>
    1.73
    </u>
    1.56
    </h3>
    1.27
    </h2>
    1.20
    </blockquote>
    1.13
    stdafx
    1.06
    Activations Density 0.004%

    No Known Activations