© 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. 34-GEMMASCOPE-RES-131K
    7. 31531
    Prev
    Next
    INDEX
    Explanations

    naming objects

    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
    Ḫ
    -0.87
    inien
    -0.82
    rechten
    -0.81
    TKey
    -0.79
    Apellido
    -0.75
     Cheval
    -0.74
    LikeLiked
    -0.74
     azeite
    -0.73
     بازدید
    -0.73
    woners
    -0.71
    POSITIVE LOGITS
     objects
    6.41
     object
    5.19
    objects
    4.41
     Objects
    4.13
     objetos
    3.91
    Objects
    3.81
    object
    3.75
    OBJECT
    3.34
     OBJECT
    3.31
     oggetti
    3.30
    Activations Density 0.186%

    No Known Activations