© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 222741
    Prev
    Next
    INDEX
    Explanations

    size and scale

    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
     enfrentar
    0.40
     estaba
    0.40
    零
    0.39
     mensagem
    0.39
    ENCED
    0.39
     আল্লাহ
    0.39
     financiero
    0.38
     แห
    0.38
    ⟦
    0.38
    Unifier
    0.37
    POSITIVE LOGITS
     disput
    0.40
     size
    0.40
     analog
    0.39
     Passenger
    0.38
    Size
    0.38
     passenger
    0.38
     lod
    0.37
    Wooden
    0.37
    lod
    0.36
     Woodlands
    0.36
    Activations Density 0.002%

    No Known Activations