© 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. 86276
    Prev
    Next
    INDEX
    Explanations

    negation or inability

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

    multi-core processors, where was, find line, a number

    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
     ethylene
    0.41
     生命周期
    0.41
    ကာ
    0.40
     oportun
    0.39
     stru
    0.39
    VECTOR
    0.39
     polarization
    0.38
    ↵↵
    0.38
     Mamm
    0.38
     during
    0.38
    POSITIVE LOGITS
     Какой
    0.45
    ड़िया
    0.44
     وين
    0.41
    ilyen
    0.41
     самую
    0.40
     Обычно
    0.40
    Какой
    0.40
     ይች
    0.40
    ˃
    0.40
    قيقة
    0.39
    Activations Density 0.005%

    No Known Activations