© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81336
    Prev
    Next
    INDEX
    Explanations

    Argued April or May

    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
     вещей
    -0.70
     Wohnung
    -0.70
     Greens
    -0.68
     thảo
    -0.68
     WINE
    -0.66
    ธ์
    -0.66
    gency
    -0.65
     Confessions
    -0.65
    äfte
    -0.64
    讚
    -0.63
    POSITIVE LOGITS
     grant
    0.76
    рат
    0.72
     dólares
    0.70
    cele
    0.69
    Qw
    0.69
    Governing
    0.66
    Preventing
    0.65
    ]?.
    0.65
     खिला
    0.64
    blank
    0.63
    Activations Density 0.072%

    No Known Activations