© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14533
    Prev
    Next
    INDEX
    Explanations

    HTML tags and content structure

    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
     such
    -1.26
     This
    -1.22
    \}.
    -1.18
    ??????
    -1.18
    ????????????????
    -1.12
     They
    -1.09
    닌
    -1.09
    ???????
    -1.08
     those
    -1.05
     %).
    -1.04
    POSITIVE LOGITS
    </h2>
    2.73
    </b>
    2.03
    </h1>
    2.00
    </strong>
    1.81
    </h3>
    1.71
    </h5>
    1.58
    </h4>
    1.55
    </i>
    1.53
    ':
    
    1.40
    </h6>
    1.30
    Activations Density 0.110%

    No Known Activations