© 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-262K
    7. 26961
    Prev
    Next
    INDEX
    Explanations

    asparagus

    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_262k_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
    糍
    0.41
     ഹിന്ദ
    0.41
    毖
    0.41
    憚
    0.40
     piya
    0.40
     inwon
    0.40
     Paise
    0.40
     kefir
    0.40
    嘜
    0.40
     Catering
    0.40
    POSITIVE LOGITS
     asparagus
    0.73
    asparagus
    0.60
    Asp
    0.54
     spears
    0.53
     Asp
    0.50
    アス
    0.50
     शता
    0.48
     stalks
    0.46
    spar
    0.45
    bundles
    0.45
    Activations Density 0.008%

    No Known Activations