© 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. 10-GEMMASCOPE-RES-131K
    7. 8256
    Prev
    Next
    INDEX
    Explanations

    word suffixes ending in ation or 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_10/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
    ”
    -1.92
    “
    -1.58
    」
    -1.49
     seleccionados
    -1.48
    F
    -1.45
     negli
    -1.45
     debido
    -1.45
    If
    -1.44
    ).
    -1.41
    P
    -1.41
    POSITIVE LOGITS
     trám
    1.57
    饧
    1.52
    ¹,
    1.50
    蹕
    1.48
     and
    1.48
     ostavi
    1.48
    ,¹
    1.45
    eluarkan
    1.41
     after
    1.40
    女主
    1.39
    Activations Density 0.252%

    No Known Activations