© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14363
    Prev
    Next
    INDEX
    Explanations

    meat and carnivore

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

    meat and poultry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蘅
    0.54
     ACLU
    0.54
     Gandh
    0.53
     phenytoin
    0.47
     Söz
    0.47
     Stars
    0.46
     न्यायालय
    0.46
     Bottle
    0.46
    涣
    0.46
     Tjiwarl
    0.46
    POSITIVE LOGITS
     meat
    1.42
    🍖
    1.41
    🥩
    1.37
    meat
    1.34
     meats
    1.32
     মাংস
    1.31
    肉
    1.28
     मांस
    1.27
    Meat
    1.25
     butcher
    1.23
    Activations Density 0.241%

    No Known Activations