© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101290
    Prev
    Next
    INDEX
    Explanations

    chat, login, searched, carcinogenic

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

    references to "chat" in software code or online discussions about chat applications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﮕ
    -3.48
    𖤍
    -3.42
     剤
    -3.42
    ſſen
    -3.34
    creenshot
    -3.31
    Ꝑ
    -3.31
    臯
    -3.30
    اتها
    -3.28
    er
    -3.28
     姆
    -3.25
    POSITIVE LOGITS
    0
    4.44
     
    4.13
    Initially
    4.03
    </strong>
    3.86
    It
    3.64
    There
    3.61
    Interestingly
    3.48
    </h3>
    3.48
    When
    3.42
    3
    3.41
    Activations Density 0.005%

    No Known Activations