© 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-16K
    7. 10827
    Prev
    Next
    INDEX
    Explanations

    gradient and derivative calculation

    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_16k_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
     φι
    0.45
     холоди
    0.38
    瓯
    0.38
     thuyết
    0.37
    ýv
    0.36
     Bose
    0.36
     темати
    0.36
    넉
    0.35
     пригла
    0.35
    يره
    0.35
    POSITIVE LOGITS
     derivative
    1.48
     derivatives
    1.39
     Derivative
    1.27
    derivative
    1.22
     gradients
    1.16
     Derivatives
    1.16
    Derivative
    1.16
     deriv
    1.12
     gradient
    1.09
     differentiation
    1.03
    Activations Density 0.156%

    No Known Activations