© 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. 83569
    Prev
    Next
    INDEX
    Explanations

    drained food items

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

    he hugs

    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
     polic
    0.48
    ίο
    0.45
    ↵
    0.43
     pointe
    0.43
     fees
    0.42
     costume
    0.42
     wines
    0.42
     contracts
    0.41
     ethers
    0.39
    `
    0.39
    POSITIVE LOGITS
    decken
    0.62
    берите
    0.55
     разнообраз
    0.54
     वेगवेग
    0.54
     рекомендации
    0.54
     приготовления
    0.54
     বেছে
    0.53
    akrishnan
    0.53
     توصیه
    0.53
    餛
    0.52
    Activations Density 0.001%

    No Known Activations