© 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. 53383
    Prev
    Next
    INDEX
    Explanations

    achievable

    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
     IncludeField
    0.44
    ᄋ
    0.43
    誣
    0.42
    ிலிருந்த
    0.39
    的原
    0.39
    deprecation
    0.39
    豈
    0.38
     первого
    0.38
     DON
    0.38
     शुक्
    0.37
    POSITIVE LOGITS
    之处
    0.45
    Att
    0.40
    äder
    0.38
     Albuquerque
    0.37
    att
    0.37
    שי
    0.36
    ixer
    0.36
    atil
    0.36
    수
    0.35
    愿意
    0.35
    Activations Density 0.017%

    No Known Activations