© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39255
    Prev
    Next
    INDEX
    Explanations

    forehead and wrinkles

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

    words and phrases related to parts of the face, particularly the forehead and eyebrows area.

    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
    la
    -1.77
    )));
    -1.61
    )\
    -1.61
    );
    -1.58
    鲠
    -1.55
    )',
    -1.54
    ).
    -1.48
    .</
    -1.44
    "".
    -1.42
    )"
    -1.41
    POSITIVE LOGITS
    戕
    1.47
     we
    1.37
    なんだろう
    1.35
    coled
    1.34
     Sử
    1.34
    方的
    1.34
    क्या
    1.32
    躰
    1.32
     usati
    1.32
     prodotto
    1.31
    Activations Density 0.037%

    No Known Activations