© 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. 109934
    Prev
    Next
    INDEX
    Explanations

    document structure separators

    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
     malloc
    -0.81
    Ghz
    -0.80
     reproach
    -0.80
    殭
    -0.77
     Obj
    -0.76
     igenom
    -0.75
    ක
    -0.75
    Fredrik
    -0.75
     necesitan
    -0.74
     känd
    -0.73
    POSITIVE LOGITS
    twist
    1.00
     will
    0.98
     twist
    0.97
     держать
    0.93
     viewers
    0.92
     intensi
    0.91
    𝒈
    0.90
     FUNDS
    0.88
     karty
    0.88
     nowe
    0.87
    Activations Density 0.004%

    No Known Activations