© 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. 118596
    Prev
    Next
    INDEX
    Explanations

    international cooperation and stated interests

    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
     may
    -1.15
     what
    -1.09
     probably
    -1.02
     either
    -1.00
     or
    -0.97
     after
    -0.97
     several
    -0.96
     just
    -0.96
     when
    -0.96
     any
    -0.95
    POSITIVE LOGITS
     hydrocarbons
    0.87
     bp
    0.86
     PRACTICAL
    0.84
     skep
    0.83
    strukturen
    0.82
    тов
    0.82
     continuer
    0.81
     Fresno
    0.81
    ortment
    0.79
     зер
    0.79
    Activations Density 0.011%

    No Known Activations