© 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. 12655
    Prev
    Next
    INDEX
    Explanations

    eating and what follows

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

    eat and what to eat

    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
    ৫
    0.68
    И
    0.67
    ک
    0.65
    Nicol
    0.62
    غیر
    0.62
    آپ
    0.62
    lbrakk
    0.62
    ৪
    0.60
    Ч
    0.59
    بيه
    0.58
    POSITIVE LOGITS
     eat
    0.86
     eating
    0.84
     Eat
    0.82
     吃
    0.80
     Eating
    0.77
     makan
    0.76
     eats
    0.73
     Ă
    0.73
    吃了
    0.72
     meals
    0.69
    Activations Density 0.064%

    No Known Activations