Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8034
    Prev
    Next
    INDEX
    Explanations

    lot or bedroom

    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
                                
    -0.93
    必须
    -0.92
    我还
    -0.91
     ciudadanos
    -0.88
    要是
    -0.88
     sprawie
    -0.88
    里面
    -0.87
     consiguió
    -0.84
    付近
    -0.84
     motyw
    -0.83
    POSITIVE LOGITS
    Hej
    0.87
    imbangan
    0.84
     iteration
    0.84
     Steen
    0.81
    poche
    0.81
     Transistor
    0.80
    Volvo
    0.79
    umque
    0.79
    truncated
    0.79
    Offered
    0.79
    Activations Density 0.030%

    No Known Activations