© 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. 75261
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
     unless
    -1.73
     Unless
    -1.38
    除非
    -1.30
     although
    -1.16
    unless
    -1.12
     only
    -1.11
    Unless
    -1.08
     except
    -1.05
     if
    -1.05
     особли
    -1.04
    POSITIVE LOGITS
    tronlink
    0.96
    ooks
    0.85
    generally
    0.85
    <{
    0.84
     nét
    0.82
    Preferred
    0.81
    daughters
    0.81
     berichten
    0.81
     WIL
    0.80
    terie
    0.80
    Activations Density 0.037%

    No Known Activations