© 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. 34-GEMMASCOPE-RES-131K
    4. 118038
    Prev
    Next
    INDEX
    Explanations

    hunger, thirst, appetite, cravings

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

    references to hunger, thirst, appetite, and food cravings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    itaria
    -0.75
    Enc
    -0.74
     Arzneimit
    -0.73
     Lucca
    -0.72
    腫
    -0.71
     Darmstadt
    -0.71
    JSONException
    -0.71
    Floor
    -0.69
    aba
    -0.69
     supplied
    -0.69
    POSITIVE LOGITS
     appetite
    3.34
     hunger
    3.33
     cravings
    2.38
     Appetite
    2.30
     thirst
    2.30
     craving
    2.25
    hunger
    2.22
     appetites
    2.11
     Hunger
    2.08
    Hunger
    2.08
    Activations Density 0.040%

    No Known Activations