© 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. 190760
    Prev
    Next
    INDEX
    Explanations

    Qualifying Exam

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

    incomplete or failed

    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
     Preto
    0.50
     प्रभ
    0.49
     पड़े
    0.48
     approached
    0.47
    㧋
    0.46
    凖
    0.46
     Rojas
    0.46
     Skywalker
    0.46
    骡
    0.45
     Peña
    0.45
    POSITIVE LOGITS
    semble
    0.52
    4
    0.49
     sonore
    0.48
    0
    0.48
     cardiaque
    0.45
    -
    0.44
    ูณ
    0.43
    शहर
    0.43
    :
    0.43
     readable
    0.43
    Activations Density 0.001%

    No Known Activations