© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98558
    Prev
    Next
    INDEX
    Explanations

    each (

    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
    電源
    -0.67
    Guer
    -0.66
     Polisi
    -0.65
    ällor
    -0.65
    /@
    -0.64
    inns
    -0.64
    rowData
    -0.63
    を入
    -0.63
    ämie
    -0.63
    Literatura
    -0.63
    POSITIVE LOGITS
     juguetes
    0.71
    𝘫
    0.67
    тесь
    0.67
    RDP
    0.66
     dag
    0.66
     درس
    0.65
     Salazar
    0.65
     Maltese
    0.65
    เข้า
    0.64
    abuhan
    0.64
    Activations Density 0.077%

    No Known Activations