© 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. 83708
    Prev
    Next
    INDEX
    Explanations

    embedding or encoding

    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
     आसपास
    0.43
    屈
    0.41
     হলেও
    0.40
     दत्ता
    0.39
     बरामद
    0.38
     welcoming
    0.37
     불구하고
    0.37
    orientation
    0.37
     പരിശോധ
    0.36
    ")):
    0.36
    POSITIVE LOGITS
    Main
    0.46
     mesma
    0.46
    THING
    0.46
     negó
    0.46
     indip
    0.46
     legenda
    0.46
     industriale
    0.46
     kati
    0.45
    THIS
    0.44
     อีก
    0.44
    Activations Density 0.002%

    No Known Activations