© 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. 75190
    Prev
    Next
    INDEX
    Explanations

    code, foreign languages, and punctuation

    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
     bazen
    -1.07
     sometimes
    -1.06
     there
    -1.04
     löst
    -1.02
     präsenti
    -1.00
     and
    -1.00
    Sometimes
    -0.98
     either
    -0.97
     bekämp
    -0.96
    iverr
    -0.96
    POSITIVE LOGITS
    yczne
    1.02
    quiry
    1.02
     muur
    1.00
    είο
    0.99
    tivité
    0.98
     koffie
    0.97
     dirigeants
    0.97
    AXI
    0.96
    場で
    0.96
    ería
    0.94
    Activations Density 0.015%

    No Known Activations