© 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. 79862
    Prev
    Next
    INDEX
    Explanations

    continue reading →

    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
     to
    -1.95
    providedIn
    -1.87
    meuble
    -1.59
    </tfoot>
    -1.43
     seleccionamos
    -1.33
    一抹
    -1.30
     It
    -1.30
     AND
    -1.30
     endforeach
    -1.28
    Really
    -1.27
    POSITIVE LOGITS
    ↵
    1.55
     やすい
    1.52
     aceste
    1.48
     dwóch
    1.41
    說
    1.39
     această
    1.39
    取り付け
    1.37
    かっ
    1.36
    ,</
    1.34
     potência
    1.34
    Activations Density 0.002%

    No Known Activations