© 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. 41-GEMMASCOPE-2-RES-262K
    7. 26391
    Prev
    Next
    INDEX
    Explanations

    antidote or antiserum

    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_all/layer_41_width_262k_l0_big
    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
    らく
    0.42
     ช่อง
    0.40
    成绩
    0.38
    เนิน
    0.38
     ሥ
    0.37
     ছই
    0.37
     screwing
    0.37
    屾
    0.36
    ครั้ง
    0.36
    弹性
    0.36
    POSITIVE LOGITS
     antidote
    2.36
     antid
    2.09
     antit
    1.23
     Ant
    1.22
     cure
    1.17
     antiserum
    1.16
     Antit
    1.15
    Ant
    1.12
     tonic
    1.10
     анти
    1.06
    Activations Density 0.004%

    No Known Activations