© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1209
    Prev
    Next
    INDEX
    Explanations

    much of a/an

    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
    龱
    -1.19
     slika
    -1.19
    eronau
    -1.17
    &
    -1.14
    postolic
    -1.12
    一点点
    -1.08
     requerida
    -1.08
     prestazioni
    -1.05
    lında
    -1.05
    摸了
    -1.05
    POSITIVE LOGITS
     a
    4.28
     an
    3.14
     sebuah
    1.29
     একটি
    1.14
    一个
    1.13
     «
    1.00
     J
    1.00
    private
    0.99
     menghar
    0.98
    !*\
    0.96
    Activations Density 0.022%

    No Known Activations