© 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. 52900
    Prev
    Next
    INDEX
    Explanations

    calculus differentiation rates

    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
    屾
    0.53
     unbounded
    0.49
     Nxd
    0.47
     ∂
    0.47
    岄
    0.45
     Grenzen
    0.44
     Derivative
    0.43
     xe
    0.43
     integração
    0.43
     hati
    0.43
    POSITIVE LOGITS
    chemicals
    0.43
    ancest
    0.40
    
    0.40
    scientists
    0.39
    Jewish
    0.39
    哲学
    0.38
    ❏
    0.38
    numbers
    0.38
    方の
    0.38
    wheeled
    0.38
    Activations Density 0.021%

    No Known Activations