© 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. 44876
    Prev
    Next
    INDEX
    Explanations

    adhere to

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

    The neuron detects occurrences of “adhere” and its morphological variants (e.g. adheres, adhered, adherence, adherent).

    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
     />}
    -1.94
     swimmer
    -1.78
    .
    -1.76
     ]);
    -1.74
    ꔹ
    -1.70
     wrestler
    -1.66
    philis
    -1.65
    imetsu
    -1.65
     />);
    -1.64
    沨
    -1.64
    POSITIVE LOGITS
    ↵
    2.25
     favoritas
    1.98
    V
    1.89
    K
    1.84
    D
    1.82
    f
    1.78
    ஂ
    1.77
    R
    1.76
    M
    1.73
    同一
    1.71
    Activations Density 0.017%

    No Known Activations