© 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. 59361
    Prev
    Next
    INDEX
    Explanations

    technical documentation and code

    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
     Mull
    -0.81
     Harrington
    -0.79
    ram
    -0.75
     merec
    -0.74
    mlung
    -0.70
     Ug
    -0.69
     unittest
    -0.68
     Mala
    -0.68
     skb
    -0.67
     MANUAL
    -0.66
    POSITIVE LOGITS
    invo
    0.73
    CIV
    0.72
    invoices
    0.71
     Ancestry
    0.71
    >):
    0.68
    geno
    0.65
     Excuse
    0.65
     GNP
    0.64
    焦
    0.62
    ginald
    0.61
    Activations Density 0.083%

    No Known Activations