© 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. 71284
    Prev
    Next
    INDEX
    Explanations

    more content or options

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

    The neuron strongly activates on instances of the word “More” (e.g. in “More Video,” “More Subscription Options,” “More Headlines,” etc.)—i.e. it detects “More” link or section headings.

    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
     The
    -1.98
     you
    -1.96
    儘
    -1.80
    ↵↵
    -1.79
     Behaup
    -1.64
     gesagt
    -1.56
     Gewähr
    -1.55
     It
    -1.55
    ]
    -1.54
     laissé
    -1.52
    POSITIVE LOGITS
     maje
    1.93
     minne
    1.76
     blanches
    1.74
     malen
    1.70
     fendi
    1.66
     kela
    1.65
     halus
    1.63
     luy
    1.63
    瘆
    1.63
     ravi
    1.62
    Activations Density 0.010%

    No Known Activations