© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2785
    Prev
    Next
    INDEX
    Explanations

    activities ending in ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.66
    ber
    -1.10
    ings
    -1.09
    bel
    -1.09
    ert
    -1.06
    ata
    -1.05
    po
    -1.03
    th
    -1.02
    pa
    -1.02
    es
    -1.00
    POSITIVE LOGITS
     in
    1.12
     prowess
    1.07
    gggg
    1.06
     with
    1.04
     around
    1.00
    意志
    1.00
     galore
    0.98
    purposes
    0.96
     pelajaran
    0.94
     during
    0.94
    Activations Density 0.070%

    No Known Activations