© 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. 22-GEMMASCOPE-RES-131K
    7. 35192
    Prev
    Next
    INDEX
    Explanations

    mathematical text

    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_22/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
     hotell
    -0.99
    ⅱ
    -0.97
    funktionen
    -0.94
    PropTypes
    -0.93
    doors
    -0.91
    umers
    -0.91
     preset
    -0.90
    eavor
    -0.90
    lac
    -0.90
     pada
    -0.90
    POSITIVE LOGITS
     because
    1.20
     this
    1.06
     we
    1.03
     both
    1.02
     well
    1.01
     such
    1.01
    するのは
    0.97
    porre
    0.96
    Oss
    0.95
     which
    0.94
    Activations Density 0.003%

    No Known Activations