© 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. 20207
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     each
    -2.08
     and
    -1.75
     to
    -1.74
     any
    -1.67
     anyone
    -1.53
     every
    -1.52
     both
    -1.46
     anybody
    -1.45
    啖
    -1.43
     každého
    -1.39
    POSITIVE LOGITS
    5
    2.22
    4
    1.82
    1
    1.72
    2
    1.72
    6
    1.70
     ſou
    1.67
     ditt
    1.66
    懨
    1.66
    3
    1.59
    떳
    1.59
    Activations Density 0.162%

    No Known Activations