© 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. 200754
    Prev
    Next
    INDEX
    Explanations

    Avengers, Speaker, researcher, nucleus

    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
    รวจ
    0.57
    㺫
    0.55
     dern
    0.53
    䊀
    0.53
     বর্বর
    0.52
    粔
    0.52
     linguistique
    0.51
    ്യ
    0.51
    舶
    0.48
     języ
    0.48
    POSITIVE LOGITS
    ’
    0.53
    '
    0.52
     impacting
    0.45
    este
    0.45
     didn
    0.44
    over
    0.44
     haven
    0.43
    aset
    0.42
     الجمهور
    0.42
     stockpile
    0.41
    Activations Density 0.001%

    No Known Activations