© 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. 128058
    Prev
    Next
    INDEX
    Explanations

    asking who or what

    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
    alanta
    -1.64
     elektrik
    -1.53
     vektor
    -1.39
    蚰
    -1.38
     CHRISTMAS
    -1.36
    rigkeit
    -1.36
     hakim
    -1.34
     ILLINOIS
    -1.34
    ???:
    -1.34
     Bulgar
    -1.33
    POSITIVE LOGITS
     a
    1.68
     people
    1.58
     çoğu
    1.45
     Öffnen
    1.44
     up
    1.42
     by
    1.41
     until
    1.38
     for
    1.36
    People
    1.30
     A
    1.28
    Activations Density 0.029%

    No Known Activations