© 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. 93500
    Prev
    Next
    INDEX
    Explanations

    code commit, his son, failing VPN

    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
     when
    0.52
     Quando
    0.51
     quando
    0.48
     kiedy
    0.48
     иногда
    0.48
    when
    0.47
     當
    0.47
     когда
    0.47
    Quando
    0.46
     cuando
    0.45
    POSITIVE LOGITS
     intimid
    0.45
    ृत
    0.43
    𝚔
    0.43
    स्ती
    0.42
    strument
    0.41
    setPrototypeOf
    0.40
    pä
    0.40
    Ethn
    0.40
     intimidate
    0.40
    ृत्य
    0.40
    Activations Density 0.005%

    No Known Activations