© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9214
    Prev
    Next
    INDEX
    Explanations

    How followed by question/instruction starters

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

    sentence openings that initiate “how”-type questions, with especially strong response to quantitative formulations.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     patrón
    0.38
     Muster
    0.37
     Anton
    0.36
    ینا
    0.36
     kiuj
    0.35
     Filho
    0.35
    ❁
    0.34
     analisar
    0.34
     фаразы
    0.34
     Bande
    0.34
    POSITIVE LOGITS
     days
    0.42
    sodium
    0.40
    th
    0.39
    to
    0.39
    R
    0.38
     octahedral
    0.37
    cost
    0.37
    three
    0.37
    n
    0.36
    time
    0.36
    Activations Density 0.020%

    No Known Activations