© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52001
    Prev
    Next
    INDEX
    Explanations

    soy sauce, tofu, or pork

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lavender
    0.50
    獼
    0.45
    ﻏ
    0.41
     Adverse
    0.41
    addDigit
    0.41
    堊
    0.41
     Itália
    0.41
     shepherds
    0.41
    loadFile
    0.41
    লাভ
    0.40
    POSITIVE LOGITS
     soy
    0.57
     noodle
    0.49
     Soy
    0.48
    Soy
    0.46
     equilib
    0.46
    油
    0.44
     kad
    0.44
     pork
    0.44
    醤油
    0.44
     Kad
    0.43
    Activations Density 0.081%

    No Known Activations