© 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. 109783
    Prev
    Next
    INDEX
    Explanations

    Plaza and words starting with Pla

    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
     Average
    -0.90
     Expected
    -0.88
    Average
    -0.85
     trató
    -0.83
     planetary
    -0.83
    rager
    -0.79
     przysz
    -0.79
     desenho
    -0.78
     average
    -0.78
     Beitrag
    -0.77
    POSITIVE LOGITS
     Pla
    0.77
     Basu
    0.76
     jane
    0.73
    Anja
    0.73
    hány
    0.73
    ierung
    0.73
    砦
    0.72
    த்தில்
    0.71
     terima
    0.71
    cnpj
    0.71
    Activations Density 0.086%

    No Known Activations