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. 7730
    Prev
    Next
    INDEX
    Explanations

    code and imports

    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
    olkata
    -0.81
    مكن
    -0.80
     sekaligus
    -0.78
    centerY
    -0.75
     собою
    -0.73
     ample
    -0.72
    がございます
    -0.71
     আপ
    -0.71
    claimers
    -0.71
    нцип
    -0.71
    POSITIVE LOGITS
    新生
    0.81
    Lan
    0.81
    RAB
    0.79
     الأد
    0.79
    bare
    0.78
    rukt
    0.77
    ité
    0.77
     recherche
    0.76
     quelles
    0.76
    𝛥
    0.75
    Activations Density 0.007%

    No Known Activations