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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 990
    Prev
    Next
    INDEX
    Explanations

    left atrium

    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_16k_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
     
    0.42
    วก
    0.41
    <u>
    0.38
     за
    0.36
     Tuna
    0.36
     기
    0.36
    alab
    0.36
    黄金
    0.35
     వ
    0.35
     کیا
    0.35
    POSITIVE LOGITS
     zarówno
    0.48
     både
    0.45
     دونوں
    0.43
     both
    0.42
     theorems
    0.42
     બંને
    0.41
     दोन्ही
    0.40
     votos
    0.40
    보다는
    0.40
     beiden
    0.40
    Activations Density 0.588%

    No Known Activations