© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118773
    Prev
    Next
    INDEX
    Explanations

    concurrent programming constructs

    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
    CONNECTED
    -0.73
    خوش
    -0.70
    rlrl
    -0.69
    occu
    -0.68
     Morde
    -0.67
     जे
    -0.67
    AKO
    -0.66
     golden
    -0.65
    GAM
    -0.65
     Semester
    -0.65
    POSITIVE LOGITS
     channels
    0.94
    channel
    0.85
    DBNull
    0.84
     await
    0.82
    offer
    0.82
     Channels
    0.80
     Chaos
    0.80
    tactos
    0.79
    send
    0.79
    ='.$
    0.79
    Activations Density 0.017%

    No Known Activations