© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9410
    Prev
    Next
    INDEX
    Explanations

    API documentation and code snippets

    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
    inverno
    -1.06
    providedIn
    -1.03
    こんばんは
    -1.00
     fhould
    -1.00
     OFFIC
    -0.98
    ᆼ
    -0.96
    leggio
    -0.96
    Treasurer
    -0.95
     katun
    -0.95
    foglio
    -0.94
    POSITIVE LOGITS
    </strong>
    0.96
    opt
    0.94
    </b>
    0.94
    ведите
    0.87
     hotel
    0.87
    ができる
    0.86
    llin
    0.86
     gehörte
    0.86
     ý
    0.85
    </i>
    0.85
    Activations Density 0.000%

    No Known Activations