© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118646
    Prev
    Next
    INDEX
    Explanations

    Titration, my order, self-contained

    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
     Kelowna
    -0.72
    wszy
    -0.71
    tiembre
    -0.69
     Kongo
    -0.68
    tä
    -0.68
    akon
    -0.68
    ⣟
    -0.68
    árez
    -0.67
    metics
    -0.67
    OCI
    -0.67
    POSITIVE LOGITS
     CONSEQU
    0.80
    绢
    0.78
     益
    0.71
     شیراز
    0.70
    ices
    0.68
    祭り
    0.68
     worked
    0.68
    μού
    0.67
     anticoag
    0.67
    ウンド
    0.67
    Activations Density 0.081%

    No Known Activations