© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113296
    Prev
    Next
    INDEX
    Explanations

    astronomical events and descriptions

    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
    ּוֹ
    -1.60
    ־ה
    -1.60
     Pedido
    -1.52
     دیگران
    -1.51
    isait
    -1.50
     Олег
    -1.50
    ：
    -1.48
    ėtų
    -1.41
    genomen
    -1.41
     γυναι
    -1.41
    POSITIVE LOGITS
    を持っている
    1.49
    これからも
    1.48
     majeurs
    1.47
     særlig
    1.45
     stanno
    1.41
    ᗜ
    1.40
     otorga
    1.40
     väga
    1.39
    According
    1.38
     religieuses
    1.38
    Activations Density 0.246%

    No Known Activations