© 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. 50839
    Prev
    Next
    INDEX
    Explanations

    determiner or linking verb followed by adjective

    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
    PLOY
    0.39
    relser
    0.38
    spersed
    0.38
    бавля
    0.37
     $)$
    0.37
    လာ
    0.36
     बन
    0.36
    JScripts
    0.35
     형
    0.35
    atat
    0.35
    POSITIVE LOGITS
     regrettable
    0.51
     tremendous
    0.50
     énorme
    0.48
    থেষ্ট
    0.48
    良い
    0.47
     जबरदस्त
    0.46
     undeniable
    0.46
     significant
    0.46
     momentous
    0.46
     considerable
    0.46
    Activations Density 0.009%

    No Known Activations