© 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. 63855
    Prev
    Next
    INDEX
    Explanations

    retrieving values or data

    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
     get
    -1.23
     gotten
    -1.13
    getting
    -1.09
     GETTING
    -0.93
    get
    -0.91
    gotten
    -0.87
     pēc
    -0.87
    得到了
    -0.86
     largely
    -0.84
    gets
    -0.83
    POSITIVE LOGITS
    уд
    0.96
     attribute
    0.87
    ())
    0.86
    attribute
    0.85
     ซ
    0.85
     mimo
    0.85
     pasajeros
    0.82
     Meilleures
    0.81
     Parts
    0.81
     Suivez
    0.81
    Activations Density 0.007%

    No Known Activations