© 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. 87056
    Prev
    Next
    INDEX
    Explanations

    strikingly different or similar

    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
     häl
    -2.67
     összefoglaló
    -2.58
    ності
    -2.58
     citado
    -2.55
     Главная
    -2.52
     szükség
    -2.34
    臵
    -2.28
    ᡴ
    -2.27
    蜕
    -2.27
     ujedno
    -2.25
    POSITIVE LOGITS
     they
    3.14
    al
    2.92
    e
    2.69
    ed
    2.52
     was
    2.44
    i
    2.39
    u
    2.34
    т
    2.34
     те
    2.31
    ?
    2.16
    Activations Density 0.001%

    No Known Activations