© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11382
    Prev
    Next
    INDEX
    Explanations

    people and pepper

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

    black pepper and piperine

    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
    년
    0.39
    년을
    0.37
    부터
    0.36
    ол
    0.36
    ул
    0.35
    נד
    0.35
    러스
    0.35
    멕
    0.35
    년부터
    0.35
    伫
    0.35
    POSITIVE LOGITS
     phag
    0.48
     annih
    0.42
     amino
    0.42
     polypeptides
    0.42
     extracellular
    0.41
     apoptotic
    0.41
     trapping
    0.40
     incest
    0.40
     abdominal
    0.40
     endogenous
    0.40
    Activations Density 0.001%

    No Known Activations