© 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. 67567
    Prev
    Next
    INDEX
    Explanations

    pending or incomplete states

    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
    ARTA
    -0.86
     fritt
    -0.84
     gång
    -0.79
     unavoidable
    -0.76
     Rouse
    -0.75
    ándote
    -0.74
     dönd
    -0.73
    losigkeit
    -0.73
     occupa
    -0.73
     dieta
    -0.73
    POSITIVE LOGITS
     chưa
    1.44
     ještě
    1.27
     هنوز
    1.20
     belum
    1.17
     yet
    1.16
     still
    1.16
     jeszcze
    1.16
     vielä
    1.16
    の準備
    1.13
     hasn
    1.10
    Activations Density 0.069%

    No Known Activations