© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11368
    Prev
    Next
    INDEX
    Explanations

    method calls

    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
     its
    -1.51
    gorra
    -1.02
     masaje
    -0.99
     imprensa
    -0.98
    lentes
    -0.97
     desfile
    -0.97
     Its
    -0.96
    骓
    -0.96
     вѣ
    -0.96
     garagem
    -0.96
    POSITIVE LOGITS
    </b>
    1.29
    </em>
    1.19
           
    1.14
    ę
    1.14
    /**
    1.09
                
    1.06
    </strong>
    1.05
    Aside
    1.04
                                
    1.03
    𝙥
    1.02
    Activations Density 0.002%

    No Known Activations