© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12281
    Prev
    Next
    INDEX
    Explanations

    words ending in -ous, -ed, -ing, -ative

    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
    mô
    -1.00
    なのは
    -0.98
    felizmente
    -0.95
    感動
    -0.94
    なのが
    -0.94
    يته
    -0.94
     sorprender
    -0.94
    fche
    -0.93
    italian
    -0.93
     muligt
    -0.92
    POSITIVE LOGITS
    嘅
    1.15
    al
    1.08
    ische
    1.03
    w
    1.00
    めの
    0.99
    en
    0.99
    ved
    0.98
    deki
    0.97
    se
    0.93
     كم
    0.93
    Activations Density 0.206%

    No Known Activations