© 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. 34-GEMMASCOPE-RES-131K
    7. 49210
    Prev
    Next
    INDEX
    Explanations

    food and drink items

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

    The neuron responds to words naming food and drink items.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     to
    -1.42
     L
    -1.04
     for
    -1.00
     przez
    -0.99
     k
    -0.98
    +
    -0.98
     W
    -0.97
     ;
    -0.97
     at
    -0.97
    +}$
    -0.95
    POSITIVE LOGITS
    various
    1.30
     termasuk
    1.30
     INCLUDING
    1.30
    including
    1.28
    Including
    1.26
     visse
    1.23
    whether
    1.22
    except
    1.22
     lavanda
    1.22
    either
    1.21
    Activations Density 0.121%

    No Known Activations