© 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. 37473
    Prev
    Next
    INDEX
    Explanations

    recommendations or profile descriptions

    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
    Ḍ
    0.46
    rictional
    0.44
    oniazid
    0.43
    EventQueue
    0.42
    CurrentByte
    0.42
     conclusive
    0.42
    apanicolaou
    0.42
    RuntimeException
    0.41
     bereaved
    0.41
    ڈن
    0.41
    POSITIVE LOGITS
     modelos
    0.49
     связано
    0.49
     влияния
    0.49
     о
    0.47
     Bulld
    0.46
     stato
    0.46
     бол
    0.46
    乃至
    0.46
     Football
    0.46
     creato
    0.46
    Activations Density 0.002%

    No Known Activations