© 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. 34-GEMMASCOPE-RES-131K
    4. 23475
    Prev
    Next
    INDEX
    Explanations

    physical quantities and 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_34/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
    に使
    -1.02
     физи
    -1.00
    に残
    -0.98
    式的
    -0.96
    »-
    -0.92
     engran
    -0.92
    ™,
    -0.91
     Жа
    -0.91
    corrhi
    -0.89
    Iv
    -0.88
    POSITIVE LOGITS
    という感じ
    1.07
    内容は
    0.98
    そのため
    0.93
    量は
    0.91
     regioni
    0.91
    遺産
    0.90
    商品は
    0.90
     Grüßen
    0.87
     density
    0.85
    などなど
    0.85
    Activations Density 0.272%

    No Known Activations