© 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. 91419
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "From"

    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
     también
    -1.23
    because
    -1.20
     después
    -1.17
     גם
    -1.16
     three
    -1.15
     також
    -1.14
     حالی
    -1.13
     também
    -1.13
     two
    -1.12
     in
    -1.11
    POSITIVE LOGITS
     the
    1.63
     here
    1.43
     experience
    1.38
     my
    1.30
     afar
    1.27
     henceforth
    1.22
     thence
    1.17
     somewhere
    1.14
     a
    1.08
    另一方面
    1.04
    Activations Density 0.024%

    No Known Activations