© 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. 10-GEMMASCOPE-RES-131K
    7. 104420
    Prev
    Next
    INDEX
    Explanations

    names that sound like common words

    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_10/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
     is
    -2.17
     you
    -1.48
    あなたは
    -1.47
    redientes
    -1.38
     I
    -1.34
     ofrecen
    -1.34
    .
    -1.33
    єте
    -1.30
     intercamb
    -1.30
    上から
    -1.29
    POSITIVE LOGITS
     that
    2.17
     their
    1.91
     Therefore
    1.78
    haviours
    1.75
    stützung
    1.66
     who
    1.63
    鸲
    1.63
    媜
    1.60
     SEÑ
    1.59
    voer
    1.58
    Activations Density 0.191%

    No Known Activations