© 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. 160467
    Prev
    Next
    INDEX
    Explanations

    projects and materials

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

    questions about products

    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
     videomuzda
    0.48
     videomuz
    0.48
     ឬ
    0.45
    🗒
    0.44
    aprendizaje
    0.43
     அமில
    0.43
     따로
    0.43
     स्ट्रीमिंग
    0.43
    儆
    0.43
    睽
    0.42
    POSITIVE LOGITS
     the
    0.55
     Nigeria
    0.54
     ollut
    0.52
     considered
    0.50
     Southeast
    0.47
     nicest
    0.47
     expectation
    0.46
     satisfaction
    0.46
     contractors
    0.46
     developer
    0.46
    Activations Density 0.001%

    No Known Activations