© 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. 25966
    Prev
    Next
    INDEX
    Explanations

    names followed by words

    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
    acaktır
    -1.11
    Nguyễn
    -1.05
     budeme
    -1.02
    .
    -0.99
     rád
    -0.98
     tunik
    -0.98
    īg
    -0.97
    úsqueda
    -0.96
     motoru
    -0.96
    letzt
    -0.94
    POSITIVE LOGITS
    is
    1.19
    r
    1.14
    not
    1.10
    日から
    1.08
    ·
    1.05
    n
    1.04
    ison
    1.03
     somehow
    1.02
    so
    1.02
    ath
    1.02
    Activations Density 0.285%

    No Known Activations