© 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. 109307
    Prev
    Next
    INDEX
    Explanations

    if membership check

    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
    uffix
    0.44
     अनो
    0.43
    different
    0.39
    itakan
    0.39
    Basically
    0.37
    searchText
    0.37
    <bos>
    0.37
    愭
    0.36
    が一
    0.36
     salicylic
    0.36
    POSITIVE LOGITS
     belong
    1.28
     belongs
    1.25
     belonged
    1.20
     belonging
    1.09
     pertenc
    1.08
    belong
    1.06
     perten
    1.05
    belongs
    1.04
     Belong
    1.04
     pertenece
    1.03
    Activations Density 0.036%

    No Known Activations