© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122995
    Prev
    Next
    INDEX
    Explanations

    blocks to, Serb population, perpetually creating

    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
    رك
    0.45
     ena
    0.44
     положения
    0.43
    ernum
    0.43
     في
    0.43
     अन्यथा
    0.42
     unwilling
    0.41
    ଡ
    0.40
     vào
    0.40
    ه
    0.40
    POSITIVE LOGITS
    żenie
    0.47
    ವುದ
    0.46
     PARA
    0.46
    ም።
    0.46
    ٰی
    0.46
     każdy
    0.46
    gus
    0.45
     Comparisons
    0.45
     หลาย
    0.45
     różnych
    0.45
    Activations Density 0.000%

    No Known Activations