© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91913
    Prev
    Next
    INDEX
    Explanations

    crucial developmental progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蓝牙
    0.49
    らす
    0.44
    ujących
    0.44
     एनिमल
    0.44
    שי
    0.43
    ोन
    0.43
    ኒ
    0.43
    OrElse
    0.42
     gesturing
    0.42
    壃
    0.41
    POSITIVE LOGITS
     pedidos
    0.43
     продукции
    0.43
    VST
    0.41
    zczeg
    0.41
     পাকিস্তানীরা
    0.39
     eigenes
    0.39
     monopolies
    0.39
    bl
    0.39
     página
    0.39
     produção
    0.38
    Activations Density 0.010%

    No Known Activations