© 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. 841
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     =
    -0.81
     yumu
    -0.77
    Computation
    -0.77
    選べる
    -0.77
    emeni
    -0.75
    Calculations
    -0.75
    thy
    -0.75
     paperwork
    -0.73
     essa
    -0.73
    ͇
    -0.72
    POSITIVE LOGITS
     snippet
    1.38
     snippets
    1.23
    snippets
    1.20
     sni
    1.14
    snippet
    1.10
    base
    1.09
     executed
    1.09
     Sni
    1.06
    snip
    1.04
    sni
    1.01
    Activations Density 0.134%

    No Known Activations