Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8491
    Prev
    Next
    INDEX
    Explanations

    background color

    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
     Lö
    -0.74
    ukup
    -0.71
    amie
    -0.71
     Fabian
    -0.70
     prestar
    -0.70
    Lö
    -0.69
    髅
    -0.68
    ributo
    -0.67
    braten
    -0.66
    <caption>
    -0.66
    POSITIVE LOGITS
     background
    5.06
     backgrounds
    4.13
    背景
    3.92
    background
    3.81
    Background
    3.59
     Background
    3.59
     backgroundColor
    3.23
     BACKGROUND
    3.22
    setBackground
    3.19
    BACKGROUND
    3.19
    Activations Density 0.161%

    No Known Activations