© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109890
    Prev
    Next
    INDEX
    Explanations

    I then statement contrast

    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
     even
    -1.86
     thậm
    -1.70
     bahkan
    -1.67
     навіть
    -1.67
     даже
    -1.64
     nawet
    -1.60
     zwar
    -1.59
     incluso
    -1.55
    虽然
    -1.50
     although
    -1.49
    POSITIVE LOGITS
     nevertheless
    2.44
     nonetheless
    2.31
     ändå
    2.05
     still
    1.84
    Nevertheless
    1.84
     trotzdem
    1.73
     comunque
    1.63
    それでも
    1.58
     dennoch
    1.56
     vẫn
    1.55
    Activations Density 0.062%

    No Known Activations