© 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. 33704
    Prev
    Next
    INDEX
    Explanations

    multinational conglomerate

    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
     MARY
    -0.74
    cose
    -0.71
    MISS
    -0.69
    rago
    -0.67
    NPR
    -0.65
    ラム
    -0.64
     мер
    -0.64
     Cato
    -0.64
     Latinoamérica
    -0.63
     vivimos
    -0.63
    POSITIVE LOGITS
    すぎた
    0.73
     celeb
    0.67
     Medications
    0.65
    旛
    0.65
    uated
    0.65
    edoria
    0.64
    atus
    0.64
    Default
    0.63
     exit
    0.63
    THREAD
    0.62
    Activations Density 0.050%

    No Known Activations