© 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. 22-GEMMASCOPE-RES-131K
    7. 14753
    Prev
    Next
    INDEX
    Explanations

    either in choices or specific examples

    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_22/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
     various
    -1.45
     supposedly
    -1.27
     .....
    -1.27
    そして
    -1.21
     which
    -1.20
     그리고
    -1.20
     people
    -1.18
     also
    -1.17
     και
    -1.16
     promotes
    -1.15
    POSITIVE LOGITS
     einerseits
    1.40
     Either
    1.31
     either
    1.22
    either
    1.20
    .!
    1.09
    specifically
    1.09
    crans
    1.09
    VERTISEMENT
    1.07
     ornate
    1.07
     spectacular
    1.06
    Activations Density 0.041%

    No Known Activations