© 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. 38542
    Prev
    Next
    INDEX
    Explanations

    bedroom, room, picture, pages, Bonus

    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
     unt
    -0.74
     sammeln
    -0.72
    mancy
    -0.69
    Nine
    -0.65
    temporada
    -0.65
    Net
    -0.65
     net
    -0.65
    pakatan
    -0.65
     Net
    -0.63
    สัม
    -0.63
    POSITIVE LOGITS
    úa
    0.83
    litis
    0.81
    Prog
    0.80
     Christiane
    0.80
    irà
    0.80
     exits
    0.79
     Lacrosse
    0.79
     EXIT
    0.77
    ｒ
    0.77
    Erreferentziak
    0.77
    Activations Density 0.002%

    No Known Activations