© 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. 34-GEMMASCOPE-RES-131K
    7. 12054
    Prev
    Next
    INDEX
    Explanations

    functional cookies usage

    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
     иск
    -0.74
    ਕ
    -0.73
     predis
    -0.72
     burials
    -0.71
     dazed
    -0.69
    IERRA
    -0.69
    cual
    -0.69
     divor
    -0.69
    škas
    -0.68
    داران
    -0.68
    POSITIVE LOGITS
     Necessary
    1.20
     functional
    1.18
     session
    1.15
    Necessary
    1.14
    necessary
    1.13
     necessary
    1.10
     Functional
    1.09
    session
    1.06
     essential
    1.00
    SESSION
    0.94
    Activations Density 0.033%

    No Known Activations