© 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. 6991
    Prev
    Next
    INDEX
    Explanations

    preceding "for"

    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
    For
    -1.72
    FOR
    -1.51
     для
    -1.44
    Для
    -1.30
     FOR
    -1.24
     For
    -1.21
    для
    -1.19
    สำหรับ
    -1.19
     Для
    -1.18
     برای
    -1.17
    POSITIVE LOGITS
     terciopelo
    0.93
     pasi
    0.93
     rall
    0.87
     makro
    0.87
    στε
    0.85
    ⎜
    0.84
    diğini
    0.84
    茕
    0.83
     acero
    0.83
    formerly
    0.83
    Activations Density 0.356%

    No Known Activations