© 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. 10-GEMMASCOPE-RES-131K
    7. 130356
    Prev
    Next
    INDEX
    Explanations

    fullscreen display

    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
    筇
    -2.14
     cruzado
    -2.09
    珦
    -2.00
     adelantado
    -1.96
     atacado
    -1.95
    を行います
    -1.95
     comunica
    -1.92
     revelado
    -1.91
     atendido
    -1.91
     firmado
    -1.88
    POSITIVE LOGITS
    with
    2.59
    6
    2.53
    8
    2.52
    5
    2.28
    ="
    2.23
    4
    2.22
    //
    2.20
    or
    2.19
    on
    2.17
    7
    2.17
    Activations Density 0.018%

    No Known Activations