© 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. 113936
    Prev
    Next
    INDEX
    Explanations

    introducing examples or comparisons

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

    The neuron selectively activates on occurrences of the word “like.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ."
    -3.70
    ).
    -3.31
    ),
    -3.25
    на
    -3.02
    the
    -2.81
    \\
    -2.77
    );
    -2.75
    ?
    -2.72
     $\
    -2.59
    ".
    -2.50
    POSITIVE LOGITS
    และ
    3.03
    儅
    2.83
    白的
    2.73
    는
    2.61
    说是
    2.59
     mismos
    2.56
    𖣘
    2.52
    ть
    2.47
     annoncé
    2.45
    
    2.44
    Activations Density 0.141%

    No Known Activations