© 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. 118772
    Prev
    Next
    INDEX
    Explanations

    RPG lore and names

    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
    兑
    -0.88
    数据
    -0.74
     给
    -0.74
    mény
    -0.73
    ünstig
    -0.73
     Shout
    -0.72
     critically
    -0.72
     piante
    -0.71
    DC
    -0.70
    Владимир
    -0.69
    POSITIVE LOGITS
     Segura
    0.82
    めます
    0.81
    Proveedor
    0.79
     Spawn
    0.79
    ccedil
    0.78
     étoient
    0.78
    viève
    0.77
    Cannabis
    0.75
    Interes
    0.75
    alers
    0.75
    Activations Density 0.013%

    No Known Activations