© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67369
    Prev
    Next
    INDEX
    Explanations

    containing or limiting spread

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

    the word "contain" and its variants, especially when followed by nouns that need to be controlled or managed.

    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
    '
    -2.13
    aimeJ
    -1.89
    każ
    -1.81
     Ibidem
    -1.79
     bemerkt
    -1.79
    頗
    -1.73
     muchacha
    -1.70
     quadrinhos
    -1.70
    渽
    -1.69
    甞
    -1.69
    POSITIVE LOGITS
    ).
    2.48
    m
    1.88
    </strong>
    1.87
     inappropri
    1.74
     “
    1.73
    ↵
    1.73
     ella
    1.72
     ۱۱
    1.70
     be
    1.67
     ۶
    1.67
    Activations Density 0.021%

    No Known Activations