Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7692
    Prev
    Next
    INDEX
    Explanations

    Q:, News:, # available

    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
     Afin
    -0.88
     Ignition
    -0.85
     econom
    -0.84
     Ibiza
    -0.83
     furn
    -0.82
     Versace
    -0.81
     Andalucía
    -0.79
     egypt
    -0.79
     Laos
    -0.79
     PMS
    -0.78
    POSITIVE LOGITS
    querySelector
    0.91
     nedenle
    0.75
    textwidth
    0.75
    responseText
    0.75
     requerido
    0.74
     comenta
    0.73
     odkry
    0.73
     elle
    0.73
    payers
    0.73
    lateinit
    0.73
    Activations Density 0.000%

    No Known Activations