© 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. 34889
    Prev
    Next
    INDEX
    Explanations

    sharing economy, same problems, Guinness World

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

    reiterate disclaimers or warnings

    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
    #$%
    0.49
    ط
    0.48
    ق
    0.47
    長
    0.47
    カスタ
    0.47
    …"
    0.46
    সাং
    0.46
    %
    0.46
     Pengh
    0.45
    جع
    0.45
    POSITIVE LOGITS
    utth
    0.54
     hashed
    0.51
     Dynam
    0.45
    klärung
    0.44
     inscr
    0.41
     잠깐
    0.41
     心
    0.41
    చేసిన
    0.40
    unnel
    0.40
    চ্ছন্ন
    0.40
    Activations Density 0.000%

    No Known Activations