Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 389
    Prev
    Next
    INDEX
    Explanations

    font size and preferred state

    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_10/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
    s
    -2.53
    y
    -2.02
     its
    -1.73
    t
    -1.68
    r
    -1.65
    en
    -1.63
    l
    -1.60
     itself
    -1.60
     it
    -1.57
    x
    -1.56
    POSITIVE LOGITS
    поги
    1.47
    klare
    1.36
     весна
    1.31
    gleichen
    1.30
    quartier
    1.28
    锕
    1.28
    atischen
    1.27
     Será
    1.26
    само
    1.24
    𖧵
    1.24
    Activations Density 0.001%

    No Known Activations