© 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. 58837
    Prev
    Next
    INDEX
    Explanations

    "Jelly Bean" or "Key Lime Pie"

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

    key aspects

    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
    a
    0.57
    el
    0.52
    drama
    0.52
     Drama
    0.46
     drama
    0.45
    oll
    0.45
     Institutes
    0.44
    eta
    0.43
    chemical
    0.43
    all
    0.43
    POSITIVE LOGITS
     tortues
    0.55
     یہودیوں
    0.54
     ኮ
    0.50
     المسي
    0.49
     نجم
    0.48
     funcionários
    0.48
     چی
    0.47
     چار
    0.46
     እንዴት
    0.46
     یہودی
    0.46
    Activations Density 0.000%

    No Known Activations