© 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. 40-GEMMASCOPE-2-RES-262K
    7. 30963
    Prev
    Next
    INDEX
    Explanations

    asking for examples

    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
     firstly
    0.57
     Firstly
    0.51
    Firstly
    0.49
    首先
    0.47
    *
    0.45
    unächst
    0.41
    一是
    0.40
    ſon
    0.40
    ose
    0.39
    ones
    0.38
    POSITIVE LOGITS
     وت
    0.42
    듣
    0.40
    浧
    0.39
     ஆனால்
    0.37
     esimerk
    0.37
     وأن
    0.37
    に関する法律
    0.36
    dataReader
    0.36
     plaintiffs
    0.36
     deceptive
    0.36
    Activations Density 0.003%

    No Known Activations