© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64662
    Prev
    Next
    INDEX
    Explanations

    anniversary or century milestones

    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
    lsch
    -0.88
     maneiras
    -0.76
     instalments
    -0.76
     يسم
    -0.75
     crónica
    -0.75
    expliquer
    -0.73
    peas
    -0.72
    yasi
    -0.72
     proverb
    -0.71
     versões
    -0.71
    POSITIVE LOGITS
     bic
    3.61
     centenary
    3.27
     Bic
    3.25
     cent
    3.11
     Centennial
    3.03
     Centen
    3.02
    Bic
    2.64
    cent
    2.48
    Cent
    2.44
     centen
    2.44
    Activations Density 0.057%

    No Known Activations