© 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. 71161
    Prev
    Next
    INDEX
    Explanations

    closing curly braces and 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_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
     télécommande
    -1.18
     Beobachtungen
    -1.09
     服务
    -1.07
    inscrire
    -1.05
     surfact
    -1.05
    undai
    -1.04
     企业
    -0.98
     oferecer
    -0.97
     jurídico
    -0.97
    などが
    -0.97
    POSITIVE LOGITS
     because
    1.23
    </i>
    1.20
    atization
    1.12
     then
    1.11
    </
    1.08
    teness
    1.07
    </em>
    1.06
     хороший
    1.04
    </strong>
    1.02
    \}$
    1.02
    Activations Density 0.027%

    No Known Activations