© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35633
    Prev
    Next
    INDEX
    Explanations

    based on sentence structure

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of a complementizer signaling the start of a subordinate or relative clause.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    aptops
    0.26
    bs
    0.25
    json
    0.23
    ar
    0.23
    ers
    0.22
     hospitalized
    0.22
     sofort
    0.22
    //}
    0.22
     স্ক্র
    0.22
    ීම්
    0.22
    POSITIVE LOGITS
    能够
    0.25
    ஃ
    0.25
    叫做
    0.24
    George
    0.24
    Based
    0.24
    དང་
    0.24
    䊂
    0.23
    名叫
    0.23
    Divine
    0.23
    William
    0.23
    Activations Density 0.054%

    No Known Activations