© 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. 130302
    Prev
    Next
    INDEX
    Explanations

    numbers and pairs

    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
     before
    -1.39
     then
    -1.37
     using
    -1.26
     previous
    -1.25
     during
    -1.22
     only
    -1.20
     due
    -1.20
     immediately
    -1.19
     important
    -1.16
     oczy
    -1.12
    POSITIVE LOGITS
    魔兽
    1.34
     nevera
    1.23
     aeroporto
    1.16
     pantalón
    1.15
    🔱
    1.11
    sometimes
    1.11
    uhnya
    1.08
     departement
    1.06
     スケッチ
    1.06
     soms
    1.06
    Activations Density 0.032%

    No Known Activations