© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42312
    Prev
    Next
    INDEX
    Explanations

    directed to or on

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

    The neuron fires on words that denote directing or concentrating something (e.g. attention, focus, effort, sights) onto a target.

    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
    .*")]
    -1.55
    ærke
    -1.51
     indicated
    -1.48
     нам
    -1.48
    riculares
    -1.48
     and
    -1.45
    aktur
    -1.45
    𝐍
    -1.44
     information
    -1.43
     allows
    -1.43
    POSITIVE LOGITS
     to
    2.16
     delightfully
    2.11
     decidedly
    2.08
    1
    1.89
     unbelievably
    1.83
     quintessential
    1.80
     deliciously
    1.80
     strikingly
    1.80
     magnificent
    1.80
     sturdy
    1.79
    Activations Density 0.019%

    No Known Activations