© 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. 51923
    Prev
    Next
    INDEX
    Explanations

    grieve

    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
     pecuniary
    0.46
     hayvan
    0.44
     animali
    0.43
     dora
    0.43
    ếc
    0.43
    ｳ
    0.43
     dieren
    0.43
     transported
    0.42
     fouled
    0.41
     zwier
    0.41
    POSITIVE LOGITS
    assembly
    0.46
    application
    0.43
    主要的
    0.42
    fluence
    0.40
    PGC
    0.40
    textfield
    0.40
    tabs
    0.40
    茉
    0.39
    案例
    0.39
    valuation
    0.38
    Activations Density 0.004%

    No Known Activations