© 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. 102989
    Prev
    Next
    INDEX
    Explanations

    alice and wonderlandalice with surnamealice and bobalice's

    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
     sababu
    -0.78
    Таким
    -0.77
     is
    -0.76
    yy
    -0.75
    piscina
    -0.75
     Manusia
    -0.74
    べく
    -0.74
    gdb
    -0.73
    џ
    -0.71
    ﾀ
    -0.71
    POSITIVE LOGITS
     Wonderland
    1.30
     wonderland
    1.16
     Alice
    1.09
    Alice
    1.05
     Lid
    0.98
    ffekt
    0.98
    дає
    0.90
    ânea
    0.90
     Faye
    0.90
     gennem
    0.87
    Activations Density 0.009%

    No Known Activations