© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11133
    Prev
    Next
    INDEX
    Explanations

    as ... as possible

    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
     and
    -2.27
    secara
    -1.62
    はコチラ
    -1.58
     修理
    -1.55
    を書く
    -1.54
    Répondre
    -1.50
    berikut
    -1.50
     mascarilla
    -1.49
     肖像
    -1.45
    Tú
    -1.41
    POSITIVE LOGITS
     to
    1.55
    c
    1.52
    n
    1.52
    w
    1.47
    su
    1.45
    e
    1.45
    g
    1.45
     those
    1.41
     Все
    1.41
    best
    1.38
    Activations Density 0.007%

    No Known Activations