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. 8688
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     this
    -1.15
    DEFAULT
    -0.98
    return
    -0.97
    properties
    -0.95
    numbers
    -0.91
    class
    -0.87
     indicated
    -0.85
     useRef
    -0.84
    While
    -0.84
    EDT
    -0.84
    POSITIVE LOGITS
     त्या
    1.02
    deres
    0.97
    chunky
    0.95
     จาก
    0.89
    "$_
    0.88
    Oslo
    0.87
    vonne
    0.87
     Aunque
    0.85
    Juven
    0.83
     unending
    0.82
    Activations Density 0.002%

    No Known Activations