© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13107
    Prev
    Next
    INDEX
    Explanations

    start of lists and phrases

    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
     in
    -1.41
     or
    -1.20
     during
    -1.16
     despite
    -1.12
     although
    -1.08
     their
    -1.06
     without
    -1.05
     and
    -1.05
     while
    -1.05
     when
    -1.03
    POSITIVE LOGITS
    Ingredienti
    1.09
    EDWARD
    1.05
     stirs
    1.03
    場合
    1.02
    意外と
    1.01
    Abbiamo
    0.97
    Zdrav
    0.97
     récol
    0.95
     attacco
    0.95
     parlare
    0.94
    Activations Density 0.000%

    No Known Activations