© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127988
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
     dopo
    -1.29
    antur
    -1.27
    付けた
    -1.27
     Übersetzung
    -1.22
    تیجه
    -1.22
    downtown
    -1.20
     sebuah
    -1.20
     órgano
    -1.20
     jego
    -1.18
     otros
    -1.12
    POSITIVE LOGITS
     “
    1.20
     Peralta
    1.05
    แล้ว
    1.02
     château
    1.01
     personel
    0.98
     hasn
    0.98
    шений
    0.98
     sonder
    0.98
     conscientious
    0.98
     oar
    0.98
    Activations Density 0.174%

    No Known Activations