© 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. 138043
    Prev
    Next
    INDEX
    Explanations

    Data Engineering, Toast, Relations, sender

    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
     Kard
    0.45
     distinguer
    0.44
    제
    0.44
     organi
    0.43
    郑
    0.43
    đa
    0.42
    zze
    0.42
     tos
    0.41
    érations
    0.41
    ட்கள்
    0.41
    POSITIVE LOGITS
    स्पून
    0.46
    鎚
    0.46
     האל
    0.45
     ViewHolder
    0.44
    ानु
    0.43
    "，
    0.42
     Geschenk
    0.41
    GetWidth
    0.41
     हेनरी
    0.41
     उन्‍ह
    0.41
    Activations Density 0.002%

    No Known Activations