© 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. 102583
    Prev
    Next
    INDEX
    Explanations

    feeding behavior or context

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

    The neuron activates for the word "feeding" and related concepts around food consumption or nutritional intake.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specifically detects occurrences of the word “feeding.”

    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
    垍
    -3.03
     they
    -2.58
    x
    -2.44
    𖣘
    -2.34
     was
    -2.33
    IN
    -2.25
    軚
    -2.25
     anún
    -2.23
    f
    -2.22
    y
    -2.22
    POSITIVE LOGITS
     Each
    2.47
     specifies
    2.38
    觏
    2.30
     знают
    2.30
     vollständ
    2.30
     Gedanke
    2.28
     ₹
    2.27
    狆
    2.27
     They
    2.25
     Einfluß
    2.25
    Activations Density 0.008%

    No Known Activations