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. 7762
    Prev
    Next
    INDEX
    Explanations

    carbon copy emails

    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
    blers
    -0.72
     Conductivity
    -0.71
     Canadiens
    -0.70
    arrière
    -0.69
    ႆ
    -0.66
     Canal
    -0.65
    clinical
    -0.64
    AppComponent
    -0.64
    disfraz
    -0.63
     đeo
    -0.63
    POSITIVE LOGITS
     cc
    5.25
    cc
    4.78
     CC
    4.28
    Cc
    3.94
    CC
    3.77
     Cc
    3.56
     copied
    3.09
     copying
    2.41
    ccs
    2.41
     copy
    2.28
    Activations Density 0.110%

    No Known Activations