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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8770
    Prev
    Next
    INDEX
    Explanations

    year or so

    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
     over
    -1.15
     potr
    -1.03
     dnes
    -0.96
     lifelong
    -0.96
    άζ
    -0.94
     gick
    -0.93
     professionnel
    -0.93
    🅂
    -0.93
    embolso
    -0.93
     scena
    -0.93
    POSITIVE LOGITS
     or
    1.57
     of
    1.41
     ago
    1.40
     especially
    1.38
     since
    1.36
    Especially
    1.31
     особенно
    1.27
    alone
    1.18
    特に
    1.13
     especialmente
    1.11
    Activations Density 0.034%

    No Known Activations