© 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. 11790
    Prev
    Next
    INDEX
    Explanations

    XML and code comments

    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
    Daf
    -0.73
    music
    -0.71
    वरण
    -0.69
     Krish
    -0.68
    手中
    -0.66
    ヴァイ
    -0.65
     maintenance
    -0.64
    を抜
    -0.63
    Redacción
    -0.62
    Exer
    -0.62
    POSITIVE LOGITS
    RATION
    0.73
    NEE
    0.71
    ucid
    0.71
    Institut
    0.68
    Ко
    0.68
    dope
    0.67
    ATURES
    0.66
    ■
    0.66
    BAR
    0.66
     lành
    0.63
    Activations Density 0.098%

    No Known Activations