© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49331
    Prev
    Next
    INDEX
    Explanations

    reported past actions or beliefs

    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
    鈊
    -1.15
     apparently
    -1.02
     realizzare
    -1.01
     caneca
    -0.98
    コラボ
    -0.97
     estadía
    -0.96
     coleção
    -0.96
    返信
    -0.95
    yaitu
    -0.95
    ционер
    -0.94
    POSITIVE LOGITS
     to
    3.67
     by
    2.05
     have
    1.82
     be
    1.28
    Have
    1.16
    tobe
    1.09
    have
    1.05
     Have
    1.02
     memiliki
    1.00
     essere
    0.96
    Activations Density 0.071%

    No Known Activations