© 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. 34-GEMMASCOPE-RES-131K
    7. 69815
    Prev
    Next
    INDEX
    Explanations

    license, version, announcement

    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_34/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
    doj
    -0.82
    izó
    -0.82
    など
    -0.78
    ၎
    -0.77
    onoi
    -0.77
     dietro
    -0.77
    𝘦
    -0.77
    flikt
    -0.74
    约定
    -0.74
    digheden
    -0.73
    POSITIVE LOGITS
    our
    0.77
    tempo
    0.76
     constituer
    0.75
     elfog
    0.74
     Datenschutz
    0.72
     Flasche
    0.72
     Begin
    0.67
    トイレ
    0.66
     quad
    0.66
    েকে
    0.66
    Activations Density 0.028%

    No Known Activations