© 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. 65512
    Prev
    Next
    INDEX
    Explanations

    closing html tags

    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
    ↵↵↵↵
    -1.40
    providedIn
    -1.39
    ↵↵↵
    -1.24
     Ensino
    -1.17
    ↵↵↵↵↵↵
    -1.11
     interesar
    -1.10
    麒麟
    -1.08
     friend
    -1.07
     Befes
    -1.05
    $=$
    -1.05
    POSITIVE LOGITS
    ↵
    2.25
    </h2>
    1.52
    </
    1.48
    ,</
    1.46
    </i>
    1.43
    </h5>
    1.40
    </b>
    1.40
     </
    1.28
     ").
    1.25
    </h3>
    1.16
    Activations Density 0.074%

    No Known Activations