© 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. 139455
    Prev
    Next
    INDEX
    Explanations

    egg whites

    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
    িলো
    0.48
    Interior
    0.44
     природных
    0.42
    Giải
    0.40
    诊断
    0.40
    真正
    0.39
    엉
    0.39
    Maria
    0.39
    Ꮫ
    0.38
    ♗
    0.38
    POSITIVE LOGITS
     beruf
    0.49
     wird
    0.44
     Juden
    0.43
    نوان
    0.40
     avoidance
    0.40
     auront
    0.40
     Multin
    0.39
     Teilnehmer
    0.39
     Angst
    0.39
     Schluss
    0.39
    Activations Density 0.010%

    No Known Activations