© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 84983
    Prev
    Next
    INDEX
    Explanations

    svg width attribute

    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_40_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
     Staying
    0.40
     Seperti
    0.39
    Staying
    0.38
    𝑻
    0.37
     Reactions
    0.37
     Thời
    0.37
     সংশ
    0.36
    φή
    0.36
     Ol
    0.36
     শ্
    0.35
    POSITIVE LOGITS
    ans
    0.44
    brough
    0.39
    пу
    0.37
    Pig
    0.37
     kain
    0.37
    ᐳ
    0.37
    Johnny
    0.36
    Pu
    0.36
    தர
    0.36
    UM
    0.35
    Activations Density 0.000%

    No Known Activations