© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11006
    Prev
    Next
    INDEX
    Explanations

    natural logarithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    daki
    2.83
    ка
    2.52
     Adapun
    2.22
     нале
    2.20
    ى
    2.17
     linearly
    2.14
     এরপর
    2.11
    色素
    2.07
     aufgel
    2.05
    orgung
    2.01
    POSITIVE LOGITS
    ⁡
    2.61
    zelfde
    2.57
    ி
    2.19
    𝑡
    2.16
    preserving
    2.15
    igner
    2.09
    ভূত
    2.09
    𝑛
    2.03
    𝑟
    2.03
    cht
    2.01
    Activations Density 0.013%

    No Known Activations