© 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. 7226
    Prev
    Next
    INDEX
    Explanations

    hiking

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

    The neuron specifically fires on mentions of hiking (e.g. the token “hiking” and its close variant “hike”).

    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
    ).
    -3.11
    ’
    -2.98
    {
    -2.83
    </h2>
    -2.81
     Importantly
    -2.72
    "
    -2.67
     This
    -2.64
     It
    -2.61
     That
    -2.61
    する
    -2.55
    POSITIVE LOGITS
    ⬮
    3.14
    Sudah
    2.67
    Hanya
    2.67
    these
    2.67
     THESE
    2.66
    菹
    2.63
    蟊
    2.58
    鹧
    2.53
    Karena
    2.52
    Bisa
    2.52
    Activations Density 0.004%

    No Known Activations