© 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. 74571
    Prev
    Next
    INDEX
    Explanations

    similar to

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

    This neuron detects numeric values (especially decimals) indicating measurements or quantities.

    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
    </h2>
    -1.82
     therefore
    -1.60
     hence
    -1.43
    ğlık
    -1.42
     thus
    -1.41
    まず
    -1.37
    D
    -1.33
    Ｄ
    -1.29
    </sup>
    -1.28
    licópter
    -1.27
    POSITIVE LOGITS
    是怎么回事
    1.55
     like
    1.48
     boasted
    1.41
     traditional
    1.39
    🪆
    1.35
    怍
    1.35
     usadas
    1.34
     the
    1.34
    䊉
    1.34
     genutzt
    1.33
    Activations Density 0.021%

    No Known Activations