© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7035
    Prev
    Next
    INDEX
    Explanations

    forming derived words with suffixes

    np_acts-logits-general · gemini-2.5-flash-lite

    forms of -ify and -ification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    억
    0.42
    爆
    0.41
    紮
    0.38
     Felix
    0.37
    nextDouble
    0.37
    ᴾ
    0.36
    ⬮
    0.36
    nativeElement
    0.36
    崧
    0.36
    rež
    0.36
    POSITIVE LOGITS
    ification
    3.22
    ified
    3.13
    ifying
    3.09
    ify
    2.84
    ifications
    2.81
    ifier
    2.78
    ifies
    2.77
    ifiers
    2.72
    ifiable
    2.39
    IFY
    2.38
    Activations Density 0.067%

    No Known Activations