© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65774
    Prev
    Next
    INDEX
    Explanations

    domain names and paths

    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
    któ
    -1.50
    の準備
    -1.48
    zdo
    -1.46
     hırka
    -1.41
    Nazwa
    -1.40
    に挑戦
    -1.38
     their
    -1.37
     Başkanı
    -1.28
    municipi
    -1.27
    𓄹
    -1.27
    POSITIVE LOGITS
    u
    1.59
    ra
    1.45
    ha
    1.41
    と
    1.37
    ca
    1.36
     alcune
    1.35
     contextLoads
    1.34
    da
    1.33
    p
    1.33
    and
    1.31
    Activations Density 0.028%

    No Known Activations