© 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. 74718
    Prev
    Next
    INDEX
    Explanations

    helps understand or choose

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

    instances of the assistant speaking about itself or its help (first-person/meta-help phrases like "I", "me", "this helps", "I will", "I can").

    oai_token-act-pair · gpt-5-mini
    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
     the
    0.50
     with
    0.49
    一
    0.46
     as
    0.45
     from
    0.45
     herm
    0.45
    完全に
    0.44
     sepenuhnya
    0.43
     trunc
    0.42
     consists
    0.42
    POSITIVE LOGITS
    echolog
    0.57
    scriber
    0.49
    নারী
    0.48
     Calyce
    0.47
     എന്ന
    0.47
    𒁹
    0.47
    ᒐ
    0.47
     erotic
    0.46
    ഷ്ണ
    0.46
    cemment
    0.46
    Activations Density 0.003%

    No Known Activations