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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76764
    Prev
    Next
    INDEX
    Explanations

    job takes time and money

    np_acts-logits-general · gemini-2.5-flash-lite

    connecting certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mile
    0.47
    ↵
    0.47
     Dor
    0.45
    aday
    0.42
    rola
    0.42
    شمند
    0.42
     belg
    0.42
     forment
    0.42
    ters
    0.41
     hein
    0.41
    POSITIVE LOGITS
    ૯
    0.52
     식
    0.50
     연결
    0.49
    洗衣
    0.49
     मौलिक
    0.48
    ဝ
    0.48
    Ẫ
    0.47
    不说
    0.46
     খাদ্য
    0.46
     aguas
    0.46
    Activations Density 0.000%

    No Known Activations