© 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. 28869
    Prev
    Next
    INDEX
    Explanations

    biological classification labels

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

    food and foreign words

    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
    อย่างไร
    0.43
     કારણે
    0.42
     steeply
    0.42
    かなか
    0.41
    🔭
    0.41
     traumatic
    0.40
    اتے
    0.40
     düşün
    0.40
     பக்க
    0.40
    发展
    0.40
    POSITIVE LOGITS
    餌
    0.51
     alimentos
    0.48
     alimento
    0.46
     seafood
    0.45
    loat
    0.44
     भोजन
    0.43
     larva
    0.43
    食用
    0.42
     entrees
    0.42
     eat
    0.42
    Activations Density 0.000%

    No Known Activations