© 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. 24933
    Prev
    Next
    INDEX
    Explanations

    last word sentences

    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
    ric
    0.43
    ørn
    0.43
    aken
    0.42
    inação
    0.42
    ᄄ
    0.42
    jski
    0.42
    充
    0.42
    iség
    0.41
    推
    0.41
    男性
    0.40
    POSITIVE LOGITS
    tenths
    0.53
     டெ
    0.50
     میلیارد
    0.50
    ר
    0.47
     инструмент
    0.46
     ሜ
    0.46
    ोबर
    0.45
    ্যে
    0.45
     ভালোবাসি
    0.44
    ર્સ
    0.44
    Activations Density 0.000%

    No Known Activations