© 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. 39229
    Prev
    Next
    INDEX
    Explanations

    resources and reading material

    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
     when
    -1.15
     during
    -1.14
    midler
    -1.10
    atschappij
    -1.09
    ;=
    -1.08
    tigheter
    -1.05
     grosir
    -1.03
    tidae
    -1.02
    ございません
    -1.02
     yaptı
    -0.97
    POSITIVE LOGITS
    especially
    1.28
     articles
    1.27
    ticularly
    1.24
    particularly
    1.16
    www
    1.16
    ぜひ
    1.10
    asca
    1.09
     WaitForSeconds
    1.09
     beż
    1.08
    Especially
    1.06
    Activations Density 0.036%

    No Known Activations