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. 7737
    Prev
    Next
    INDEX
    Explanations

    RT followed by specific terms

    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
     funzione
    -0.79
    focusable
    -0.75
    lagten
    -0.71
     mỏng
    -0.70
    kó
    -0.70
     assault
    -0.70
    ന്റെ
    -0.69
    ᴴ
    -0.68
    asting
    -0.68
     مبارک
    -0.68
    POSITIVE LOGITS
     Rt
    0.87
     Priests
    0.81
     rt
    0.79
    🟢
    0.75
     Goats
    0.74
     RT
    0.74
    Longrightarrow
    0.73
     Plastic
    0.73
     Painters
    0.73
    ⛪
    0.73
    Activations Density 0.031%

    No Known Activations