© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13603
    Prev
    Next
    INDEX
    Explanations

    relevant to

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

    The neuron detects occurrences of the word “relevant” (i.e. when something is described as relevant to a context).

    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
     extremamente
    -3.08
    "}
    -2.89
    </i>
    -2.88
    萇
    -2.78
    archiwizowane
    -2.77
     literalmente
    -2.75
    ";
    -2.67
     are
    -2.63
     bleak
    -2.63
    
    -2.59
    POSITIVE LOGITS
     That
    3.06
    X
    2.78
    M
    2.77
     Surprisingly
    2.75
    .
    2.72
    H
    2.69
     Trying
    2.66
    Even
    2.64
     coincident
    2.63
    just
    2.61
    Activations Density 0.008%

    No Known Activations