© 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. 52988
    Prev
    Next
    INDEX
    Explanations

    the followed by certain words

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

    living in accordance with nature

    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
     ominous
    0.49
     möglichen
    0.48
     painfully
    0.46
    ವರೆಗೆ
    0.45
    穹
    0.43
     unsettling
    0.42
     insidious
    0.42
     impactos
    0.42
     eure
    0.41
     echoed
    0.41
    POSITIVE LOGITS
    苏州
    0.48
    GNU
    0.45
    !(
    0.44
    друг
    0.43
     ظاہر
    0.42
    -(
    0.41
     വാങ്ങ
    0.41
    ,(
    0.41
    北京市
    0.40
    绣
    0.40
    Activations Density 0.000%

    No Known Activations