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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8003
    Prev
    Next
    INDEX
    Explanations

    place names starting with Es, Au, Av, Ed, Et, Aj, Az, En, Ani

    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
    姿勢
    -0.85
     birra
    -0.82
    以外
    -0.81
    owning
    -0.77
     orchestra
    -0.77
    を
    -0.77
    Rm
    -0.74
    最後は
    -0.74
    これも
    -0.73
     utom
    -0.73
    POSITIVE LOGITS
    争议
    0.83
    niczka
    0.81
    wami
    0.80
    ّد
    0.80
    際は
    0.80
     PHYSICAL
    0.75
     edifice
    0.75
    ciencia
    0.75
    PART
    0.73
     即
    0.73
    Activations Density 0.055%

    No Known Activations