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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118688
    Prev
    Next
    INDEX
    Explanations

    javascript module exports

    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
     (
    -1.05
    之类的
    -0.93
    $
    -0.93
    ((
    -0.92
     Ministro
    -0.92
    $(".
    -0.90
    '
    -0.88
     ("
    -0.88
    但这
    -0.88
     had
    -0.85
    POSITIVE LOGITS
    }}+\
    1.16
    )}+\
    1.09
    hetically
    1.02
    豋
    1.02
    cocina
    1.01
     concentrado
    1.01
    なのでしょう
    1.00
    crí
    0.99
    món
    0.99
     quella
    0.99
    Activations Density 0.014%

    No Known Activations