© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 59875
    Prev
    Next
    INDEX
    Explanations

    continue to

    np_acts-logits-general · gemini-2.5-flash-lite

    US political and economic sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CERT
    0.55
    of
    0.52
    9
    0.49
    6
    0.49
     કર્મ
    0.48
    ফ
    0.48
    cyt
    0.48
    ラック
    0.47
    4
    0.46
    eningkatan
    0.46
    POSITIVE LOGITS
     run
    0.45
     antecedent
    0.44
    垍
    0.42
     errands
    0.42
     తమ
    0.39
     errand
    0.39
     inference
    0.39
     tamper
    0.39
    的消息
    0.39
     Affairs
    0.39
    Activations Density 0.000%

    No Known Activations