© 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. 124703
    Prev
    Next
    INDEX
    Explanations

    ensure that

    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
    鼕
    -1.70
     також
    -1.58
     reklama
    -1.55
    řejmě
    -1.53
    gı
    -1.48
    内心
    -1.42
    ∽
    -1.42
    kurtka
    -1.41
    たちも
    -1.41
    蹰
    -1.41
    POSITIVE LOGITS
     who
    1.75
     how
    1.63
     which
    1.50
    ↵
    1.45
     whose
    1.45
     he
    1.44
    and
    1.38
     was
    1.36
    who
    1.33
    *
    1.33
    Activations Density 0.014%

    No Known Activations