© 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. 223175
    Prev
    Next
    INDEX
    Explanations

    date and abbreviation

    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
     buffs
    0.40
     ered
    0.39
     commanded
    0.38
    粋
    0.38
    ಂಥ
    0.37
     buff
    0.37
     buf
    0.36
     unordered
    0.36
     beck
    0.36
     কৰি
    0.36
    POSITIVE LOGITS
    淪
    0.45
    %\
    0.43
    डे
    0.39
     &(
    0.39
    &(
    0.39
     Transl
    0.37
     Pol
    0.37
    жаем
    0.37
     Filtering
    0.37
     αγ
    0.37
    Activations Density 0.000%

    No Known Activations