© 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. 54068
    Prev
    Next
    INDEX
    Explanations

    common word endings

    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
    տ
    -1.00
    sso
    -1.00
    tr
    -0.99
    etting
    -0.96
    pecific
    -0.96
    ta
    -0.94
    tui
    -0.94
    ec
    -0.92
    truct
    -0.92
    plit
    -0.91
    POSITIVE LOGITS
     Literal
    0.88
    нение
    0.86
     Dropbox
    0.81
    jada
    0.79
    olds
    0.79
    กรรม
    0.79
     '__
    0.75
    ணை
    0.74
    ataire
    0.74
     diario
    0.73
    Activations Density 0.142%

    No Known Activations