© 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. 99871
    Prev
    Next
    INDEX
    Explanations

    commas

    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
    izability
    -1.02
     bedste
    -1.00
    itisation
    -0.98
    tiness
    -0.94
     プリーツ
    -0.93
    otry
    -0.92
     incess
    -0.92
     stric
    -0.92
     dochter
    -0.91
    asibility
    -0.91
    POSITIVE LOGITS
     durable
    1.33
     yet
    1.26
     efficient
    1.22
     informative
    1.16
     nutritious
    1.14
     stable
    1.11
     like
    1.11
     but
    1.09
     noisy
    1.04
     predictable
    1.02
    Activations Density 0.093%

    No Known Activations