© 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. 109792
    Prev
    Next
    INDEX
    Explanations

    data interchange or Q:

    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
    larna
    -0.76
     praise
    -0.75
     baloncesto
    -0.74
     tief
    -0.73
     BigDecimal
    -0.72
     lobos
    -0.71
     hwnd
    -0.71
     epidermal
    -0.71
     Budapest
    -0.70
     congenital
    -0.70
    POSITIVE LOGITS
    pb
    0.82
    DebuggerNonUser
    0.81
    HOL
    0.81
    תיים
    0.81
    さに
    0.80
    齬
    0.79
    sharp
    0.79
    eeded
    0.78
     큰
    0.78
     Dosto
    0.76
    Activations Density 0.008%

    No Known Activations