© 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. 110456
    Prev
    Next
    INDEX
    Explanations

    Label Definition

    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
     Careers
    -0.84
     Савезне
    -0.84
     on
    -0.83
     all
    -0.81
     bisnis
    -0.77
    Kie
    -0.76
     even
    -0.75
     or
    -0.74
    عار
    -0.74
    قاط
    -0.73
    POSITIVE LOGITS
    might
    0.85
     gravely
    0.82
    especially
    0.82
    Standort
    0.81
    Lebens
    0.79
    mainly
    0.79
    それぞれの
    0.79
     sumamente
    0.78
    particularly
    0.77
    could
    0.77
    Activations Density 0.004%

    No Known Activations