© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13223
    Prev
    Next
    INDEX
    Explanations

    template, quest, STEM, sponsor, forms

    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
     and
    -2.16
     this
    -1.48
     or
    -1.47
    egli
    -1.36
    рі
    -1.34
    硏
    -1.32
    penser
    -1.27
    perto
    -1.26
    styrene
    -1.24
    มาณ
    -1.23
    POSITIVE LOGITS
     a
    1.70
     $
    1.60
    _
    1.56
    vább
    1.51
    dienne
    1.41
     lâmpada
    1.38
     escreveu
    1.38
     lavable
    1.37
    ibility
    1.34
     apaixon
    1.34
    Activations Density 0.123%

    No Known Activations